Reference curve acquisition method and device, detection method, storage medium and equipment
By acquiring and correcting historical parameter data of photovoltaic power plants, a more realistic baseline curve is generated, which solves the problem of inaccurate detection caused by baseline curve deviation in existing technologies, and improves the accuracy of photovoltaic module fault detection and operation and maintenance support.
Patent Information
- Application Number
- CN202410918472.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-09
- Publication Date
- 2024-11-15
AI Technical Summary
Due to factors such as climate conditions and the accuracy of irradiation meters, the baseline curve obtained using the clear sky model in existing technologies deviates from the baseline curve of photovoltaic power plants under actual conditions, resulting in inaccurate detection of photovoltaic module faults.
By acquiring historical parameter data of the target photovoltaic power station, the theoretical reference curve is corrected using the sunny day reference curve to obtain a target reference curve that is more in line with the actual situation, including the target irradiance reference curve and the target power reference curve.
It improves the accuracy and applicability of photovoltaic module fault detection, provides more accurate photovoltaic power plant operation and maintenance data support, and enhances the reliability of detection.
Smart Images

Figure CN118966515A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of photovoltaic power generation technology, and in particular to a reference curve acquisition method, device and detection method, storage medium and equipment. Background Art
[0002] In the current data-driven context, photovoltaic module fault detection technology has shown a diversified development trend. Among these technologies, a widely used strategy is to compare the actual curve of the parameters collected during the actual operation of the equipment with the preset benchmark curve to determine the abnormal detection result of the equipment. In the field of photovoltaic power generation technology, the benchmark curve is the photovoltaic module benchmark curve obtained by applying the clear sky model of the photovoltaic module, such as the irradiation benchmark curve, the power benchmark curve, etc. However, due to the influence of the inherent characteristics of the photovoltaic power station (such as climatic conditions, irradiator accuracy, etc.), the benchmark curve obtained by using the clear sky model may deviate from the actual benchmark curve of the photovoltaic power station under the actual environment, which may lead to inaccurate detection. Summary of the invention
[0003] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the purpose of the present application is to propose a reference curve acquisition method, storage medium and electronic device to obtain a target reference curve that is more in line with the actual situation of a photovoltaic power station, which helps to improve the accuracy of subsequent photovoltaic module fault detection.
[0004] In a first aspect, the present application proposes a method for obtaining a benchmark curve, comprising: obtaining historical parameter data of a target photovoltaic power station; obtaining a sunny day benchmark curve of the target photovoltaic power station based on the historical parameter data, wherein the historical parameter data includes historical irradiation data and / or historical power generation data; using the sunny day benchmark curve to correct a theoretical benchmark curve to obtain a target benchmark curve, wherein the theoretical benchmark curve is obtained using a clear sky model, and the target benchmark curve includes a target irradiation benchmark curve and / or a target power benchmark curve.
[0005] In addition, the reference curve acquisition method of the embodiment of the present application may also have the following additional technical features:
[0006] According to one embodiment of the present application, the historical parameter data includes irradiation data within a preset historical time period; obtaining the sunny day reference curve of the target photovoltaic power station based on the historical parameter data includes: dividing the preset historical time period into multiple sub-time periods; for each moment in each sub-time period, taking the maximum value of the irradiation data at that moment in the multiple sub-time periods as the target irradiation value at that moment; and obtaining the sunny day irradiation reference curve based on the target irradiation value.
[0007] According to one embodiment of the present application, obtaining a sunny day irradiance reference curve according to the target irradiance value includes:
[0008] The sunny day irradiation reference curve is determined according to all obtained moments and their corresponding target irradiation values.
[0009] According to one embodiment of the present application, the historical parameter data includes power generation data within a preset historical time period, and the target photovoltaic power station includes multiple photovoltaic strings; the sunny day reference curve of the target photovoltaic power station is obtained based on the historical parameter data, including: dividing the preset historical time period into multiple sub-time periods; for each moment in each sub-time period, the maximum value of the power generation data of the multiple photovoltaic strings in the sub-time period at that moment is used as the first target power generation value of the sub-time period at that moment, and for each moment in the multiple sub-time periods, the maximum value of the first target power generation value at that moment in the preset historical time period is used as the second target power generation value at that moment; and the sunny day power reference curve is obtained according to the second target power generation value.
[0010] According to an embodiment of the present application, obtaining a sunny day power reference curve according to the second target power generation value includes: determining the sunny day power reference curve according to all obtained moments and their corresponding second target power generation values.
[0011] According to an embodiment of the present application, the use of the sunny day reference curve to correct the theoretical reference curve includes: dividing the sunny day reference curve and the theoretical reference curve into multiple intervals based on time; for each interval, calculating the ratio between the parameter value at each time point on the sunny day reference curve and the parameter value at each time point on the theoretical reference curve within the interval, and obtaining the median of all ratios within the interval; obtaining a total difference coefficient based on multiple medians corresponding to multiple intervals, and using the total difference coefficient to correct the theoretical reference curve.
[0012] According to one embodiment of the present application, before calculating the ratio between the parameter value at each time point on the sunny day benchmark curve within the interval and the parameter value at each time point on the theoretical benchmark curve, the method also includes: determining that the interval is a target interval, and the parameter value at each time point within the target interval is greater than a preset parameter threshold; wherein, correcting the theoretical benchmark curve using the total difference coefficient includes: correcting the theoretical benchmark curve within each target interval using the total difference coefficient.
[0013] According to one embodiment of the present application, the method also includes: comparing the total difference coefficient with a preset coefficient threshold; if the total difference coefficient is less than or equal to the preset coefficient threshold, executing the step of correcting the theoretical reference curve using the total difference coefficient; if the total difference coefficient is greater than the preset coefficient threshold, increasing the backtracking time of the historical parameter data and returning to the step of obtaining the historical parameter data of the target photovoltaic power station.
[0014] In the second aspect, the present application proposes a benchmark curve acquisition device, comprising: an acquisition module, used to acquire historical parameter data of a target photovoltaic power station, wherein the historical parameter data includes historical irradiation data and / or historical power generation data; a processing module, used to obtain a sunny day benchmark curve of the target photovoltaic power station based on the historical parameter data; a correction module, used to use the sunny day benchmark curve to correct a theoretical benchmark curve to obtain a target benchmark curve, wherein the theoretical benchmark curve is obtained using a clear sky model, and the target benchmark curve includes a target irradiation benchmark curve and / or a target power benchmark curve.
[0015] In a third aspect, the present application proposes a photovoltaic module fault detection method, comprising: performing photovoltaic module fault detection using a target reference curve obtained by the reference curve acquisition method described in the first aspect.
[0016] In a fourth aspect, the present application proposes a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the reference curve acquisition method described in the first aspect above, or the photovoltaic component fault detection method described in the third aspect above is implemented.
[0017] In a fifth aspect, the present application proposes an electronic device, comprising a memory, a processor, and a computer program stored on the memory. When the computer program is executed by the processor, it implements the reference curve acquisition method described in the first aspect above, or the photovoltaic component fault detection method described in the third aspect above.
[0018] The reference curve acquisition method, device and detection method, storage medium and equipment of the embodiments of the present application first obtain historical parameter data of the target photovoltaic power station, and then obtain the sunny day reference curve of the target photovoltaic power station based on the historical parameter data. Thereafter, the theoretical reference curve is corrected using the sunny day reference curve to obtain a target reference curve that is more in line with the actual situation of the target photovoltaic power station, thereby improving the accuracy of the sunny day reference curve of the target photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 is a flow chart of a method for obtaining a reference curve according to an embodiment of the present application;
[0020] Figure 2 is a flow chart of a method for obtaining a reference curve according to a specific embodiment of the present application;
[0021] Figure 3 is a flow chart of a method for obtaining a reference curve according to another embodiment of the present application;
[0022] FIG4( a ) is a schematic diagram of historical irradiation data of an example of the present application;
[0023] FIG4( b ) is a schematic diagram of a sunny day irradiance reference curve obtained based on FIG4( a );
[0024] Figure 5 This is a flowchart of obtaining a sunny day reference curve according to an example of the present application;
[0025] Figure 6 is a schematic diagram of a sunny day reference curve and a theoretical reference curve of an example of the present application;
[0026] Figure 7 is a schematic diagram of a sunny day reference curve, a theoretical reference curve and a target reference curve of an example of the present application;
[0027] Figure 8 This is a flowchart of an example of using a sunny day reference curve to correct a theoretical reference curve in the present application;
[0028] Fig. 9 is a structural block diagram of an electronic device according to an embodiment of the present application;
[0029] Fig.10 It is a structural block diagram of the reference curve acquisition device of an embodiment of the present application. DETAILED DESCRIPTION
[0030] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.
[0031] Due to differences in geographical location, climate conditions, hardware configuration and some other factors of photovoltaic power stations, there is a deviation between the sunny day benchmark curve of photovoltaic power stations in actual environments and the theoretical curve obtained from the clear sky model of photovoltaic modules.
[0032] To address this problem, the present application proposes a method for obtaining a reference curve, which fine-tunes the reference curve obtained from the clear sky model of photovoltaic modules based on the historical data of photovoltaic power stations, thereby obtaining an adaptive reference curve that is more suitable for the actual conditions of photovoltaic power stations, which may include an irradiation reference curve and a power reference curve. This method aims to improve the accuracy and applicability of photovoltaic module fault detection by obtaining a more accurate theoretical reference benchmark. It can also be used for real-time photovoltaic power generation weather type assessment, power generation model calculation, etc., to provide more accurate data support for photovoltaic power station operation and maintenance. Based on the reference curve acquisition method, the present application also proposes a storage medium and an electronic device.
[0033] The following describes the reference curve acquisition method, storage medium and electronic device of the embodiments of the present application with reference to the accompanying drawings.
[0034] Figure 1 It is a flowchart of a reference curve acquisition method according to an embodiment of the present application, and the method can be executed by an electronic device.
[0035] like Figure 1 As shown, the reference curve acquisition method includes:
[0036] S11, obtaining historical parameter data of a target photovoltaic power station.
[0037] Specifically, the target photovoltaic power station may be a photovoltaic power station for which an accurate reference curve is required, and may be selected as required. The historical parameter data may include the irradiation data (i.e., solar irradiation data) and / or power generation data of the target photovoltaic power station in a preset historical time period (e.g., the past n days). For example, if an accurate irradiation reference curve is required, the historical parameter data includes the irradiation data of the target photovoltaic power station in the past n days; if an accurate power reference curve is required, the historical parameter data includes the power generation data of the target photovoltaic power station in the past n days; if an accurate irradiation reference curve and power reference curve are required, the historical parameter data includes the irradiation data and power generation data of the target photovoltaic power station in the past n days.
[0038] Wherein, n is an integer greater than 1, such as 5, 10, 15, etc., which can be set specifically as needed. The irradiation data can be collected by an irradiator or an irradiation sensor, and can be transmitted to an electronic device or other database (such as an inverter database of a target photovoltaic power station) for storage through a wireless or wired communication module, and called by an electronic device when the execution conditions of the benchmark curve acquisition method are met. The power generation data can be calculated by the operating data of the target photovoltaic power station (such as the operating current and operating voltage of each photovoltaic module), and the operating data can be collected by a corresponding data acquisition module. A processing device can be set corresponding to the operating data to obtain the power generation data according to the operating data, and then the power generation data is first transmitted to an electronic device or other database (such as an inverter database of a target photovoltaic power station) for storage, and when the execution conditions of the benchmark curve acquisition method are met, it is called by an electronic device.
[0039] S12, obtaining a sunny day reference curve of the target photovoltaic power station according to the historical parameter data.
[0040] Specifically, the sunny day reference curve may include a sunny day irradiance reference curve and / or a sunny day power reference curve.
[0041] As an implementation method, the historical parameter data includes irradiation data within a preset historical time period. Due to the large fluctuations in weather changes during a day, it is difficult to obtain a stable sunny day reference irradiation curve on a specific day. For this reason, the present application adopts a method of obtaining the maximum irradiation value at each moment in the historical irradiation data of multiple days to form a stable sunny day irradiation benchmark for the entire day. In other words, the sunny day reference curve of the target photovoltaic power station is obtained according to the historical parameter data, including: dividing the preset historical time period into multiple sub-time periods; for each moment in each sub-time period, taking the maximum value of the irradiation data at that moment in the multiple sub-time periods as the target irradiation value at that moment; and obtaining the sunny day irradiation reference curve according to the target irradiation value.
[0042] Wherein, obtaining a sunny day irradiation reference curve according to the target irradiation value may include: determining the sunny day irradiation reference curve according to all obtained moments and their corresponding target irradiation values. For example, a curve may be drawn with time as the horizontal axis and irradiation value as the vertical axis.
[0043] Specifically, due to the fluctuation of real-time weather conditions, the data collected in different time periods will change significantly. For example, the preset historical time period is the past n days, and the preset historical time period can be divided into n sub-time periods, each of which is one day. The period from A to B on the first day may experience a change from sunny to cloudy, resulting in a decrease in irradiance, while the period from A to B on the second day may experience a change from cloudy to sunny, resulting in an increase in irradiance. By selecting the maximum value of irradiance at each time point in the historical data of multiple days as the expectation, the value on the irradiance reference curve is obtained, and on the basis of selecting the irradiance of a sufficient number of historical days, a more reasonable sunny day irradiance reference curve can be constructed. Specifically, the irradiance data of the selected preset historical time period can be read, and for each moment in the sub-time period, the irradiance value at the same moment of the n-day data is compared, and the maximum value is selected as the irradiance value at this moment in the sunny day irradiance reference curve. When all moments are traversed for the n-day data, the reference irradiance of the entire period is obtained, and then the sunny day irradiation reference curve is obtained.
[0044] As another embodiment, the historical parameter data includes power generation data within a preset historical time period, and the target photovoltaic power station includes multiple photovoltaic strings. Similar to the above-mentioned irradiation data processing, by analyzing the maximum power generation values of multiple photovoltaic strings at each time point in multiple historical days, a power generation benchmark under stable sunny conditions throughout the day is formed. In other words, the sunny day benchmark curve of the target photovoltaic power station is obtained according to the historical parameter data, including: dividing the preset historical time period into multiple sub-time periods; for each moment in each sub-time period, the maximum value of the power generation data of multiple photovoltaic strings at that moment in the sub-time period is used as the first target power generation value at that moment in the sub-time period, and the maximum value of the first target power generation value at that moment in multiple sub-time periods is used as the second target power generation value at that moment; and the sunny day power benchmark curve is obtained according to the second target power generation value.
[0045] Wherein, obtaining the sunny day power reference curve according to the second target power generation value includes: determining the sunny day power reference curve according to all obtained moments and their corresponding second target power generation values. For example, a curve can be drawn with time as the horizontal axis and power generation value as the vertical axis.
[0046] Similarly, due to fluctuations in real-time weather conditions, data collected in different time periods will vary significantly. For example, the weather from period A to period B on the first day may change from sunny to cloudy, resulting in a decrease in power generation, while the weather from period A to period B on the second day may change from cloudy to sunny, resulting in an increase in power generation. By selecting the maximum power generation at each time point in the multi-day historical data as the expectation, obtaining the value on the sunny power reference curve, and selecting the power generation data of a sufficient number of historical days, a more reasonable sunny power reference curve can be constructed.
[0047] It should be noted that since the target photovoltaic power station contains multiple photovoltaic strings, when the target photovoltaic power station area spans a large area, the power generation of different photovoltaic strings at the same time may be quite different. In order to eliminate the power deviation caused by the different positions of the photovoltaic strings, the cleaning operations in actual operation and maintenance, and the influence of some other factors on the power generation, before comparing the multi-day dimension, as many photovoltaic string data as possible can be selected, and the maximum power generation of different photovoltaic strings can be selected for each same time between each photovoltaic string as the normal value of the data of the day (can also be recorded as a reference value), which is used as the power data that best reflects the actual sunny working conditions. Afterwards, similar to the method of obtaining the benchmark irradiation, for these n days, based on the normal values selected between the components, the maximum value at each same time of these n days is obtained, and the benchmark power of the whole day is obtained, and then the sunny power benchmark curve is obtained.
[0048] As another implementation, the historical parameter data includes irradiation data and power generation data within a preset historical time period; the sunny day reference curve includes the above-mentioned sunny day irradiation reference curve and sunny day power reference curve.
[0049] S13, using the clear sky reference curve to correct the theoretical reference curve to obtain a target reference curve, wherein the theoretical reference curve is obtained using a clear sky model.
[0050] The target reference curve includes a target irradiation reference curve and / or a target power reference curve.
[0051] Specifically, the clear sky model refers to a model that can directly calculate the direct solar radiation using theoretical formulas when the sky is clear and cloudless, and may include the ASHRAE model, the Bird model, etc. The clear sky model can be used to obtain the theoretical reference curve of the target photovoltaic power station in the set period according to the solar altitude angle at different times in the set period under the condition of sunny weather on the same day, and the set period is the same as the period corresponding to the clear sky reference curve. The theoretical reference curve can be corrected using the clear sky reference curve obtained according to the historical parameter data of the target photovoltaic power station, such as calculating the deviation coefficient between the two curves (the data of multiple points in time on the two curves can be taken to calculate the ratio, difference, etc., and then the mean of the ratio and the mean of the difference can be calculated as the deviation coefficient), and then the theoretical reference curve can be corrected based on the deviation coefficient, so as to obtain a target reference curve that is more accurate and closer to the actual situation of the target photovoltaic power station relative to the theoretical reference curve, so as to provide more accurate data support for the operation and maintenance of the target photovoltaic power station, which is helpful to improve the accuracy of photovoltaic module fault detection.
[0052] Take historical parameter data including irradiation data and power generation data as an example. Figure 2 As shown, the reference curve acquisition method includes:
[0053] S21, obtaining historical irradiation data and historical power generation data of the target photovoltaic power station, and obtaining a sunny day irradiation reference curve according to the historical irradiation data and a sunny day power reference curve according to the historical power generation data.
[0054] S22, using the clear sky model to calculate the theoretical irradiation reference curve of the target photovoltaic power station on that day, and deriving the theoretical power reference curve of that day based on the theoretical irradiation reference curve.
[0055] S23, using the sunny day irradiation reference curve to correct the theoretical irradiation reference curve to obtain a target irradiation reference curve, and using the sunny day power reference curve to correct the theoretical power reference curve to obtain a target power reference curve.
[0056] In some embodiments of the present application, in order to facilitate obtaining a sunny day reference curve and improve the accuracy of the obtained sunny day reference curve, as shown in FIG. Figure 3 As shown, before obtaining the sunny day reference curve of the target photovoltaic power station according to the historical parameter data, the reference curve acquisition method further includes:
[0057] S14, performing at least one of data verification, data period screening and data time alignment processing on the historical parameter data.
[0058] Specifically, data verification mainly includes two verification methods: 1) Verify whether the data is incomplete (or missing) due to the failure of the data acquisition module or communication module. If so, discard the days with incomplete data. 2) Verify whether the data is abnormal due to the failure of the irradiator and photovoltaic inverter. When an abnormal value is detected, the average of the previous and next values of the current abnormal value can be used to replace the current abnormal value; when multiple abnormal values appear continuously, the previous normal value is used to replace the abnormal value.
[0059] Data time period screening is mainly due to the fact that the photovoltaic inverter does not work before sunrise and after sunset on the same day. Therefore, for daily data, the data within the specified time period can be screened and processed based on the time field.
[0060] The data time alignment process is mainly due to the fact that the photovoltaic inverter may start at different times every day, and the nodes at which data collection starts may be different, resulting in the collected data not being uniform in the time field. Therefore, in order to facilitate the subsequent data processing, the data needs to be time aligned. The specific process includes: traversing the currently selected n days of data, finding the earliest time point in the starting value of each day's data (or randomly selecting the earliest time point of a certain day) as the reference time starting point. Based on the reference time starting point, calculate the deviation value between the starting time points of other days and the reference time point in turn, and based on the deviation value, subtract the deviation value from each timestamp on the data of other days. Finally, the selected n days of data are aligned in the time field.
[0061] Since the sunny day reference curve obtained in step S12 can be generated based on the fusion of cross-day data, and the granularity of the sampled data is relatively fine, the difference in weather conditions on different days will produce greater volatility in the fine-grained data. The ideal reference curve should be smooth, so it is necessary to smooth the currently obtained sunny day reference curve to facilitate the subsequent correction of the theoretical reference curve.
[0062] In some embodiments of the present application, before the sunny day reference curve is used to correct the theoretical reference curve corresponding to the historical parameter data, the sunny day reference curve is also smoothed.
[0063] Specifically, at least one of the mean filtering method, the median filtering method, and the Gaussian filtering method can be used to smooth the sunny day reference curve. Considering that cross-day data fusion may cause data fluctuations to intensify, a single smoothing method may not be able to effectively mitigate this volatility, that is, it is difficult to effectively smooth the current data. To this end, the present application proposes an enhanced smoothing strategy, namely a combined sliding window smoothing algorithm, which combines multiple smoothing strategies to more accurately and effectively eliminate irregular fluctuations in the data and ensure that the obtained sunny day reference curve can be effectively smoothed. In other words, the sunny day reference curve is smoothed, including: using a target sliding window and a target smoothing value corresponding to the target sliding window to smooth the sunny day reference curve, wherein the target smoothing value is obtained based on at least two of the mean smoothing value, the median smoothing value, and the Gaussian smoothing value calculated based on the corresponding target sliding window, and the size and step size of the target sliding window can be set as needed.
[0064] Taking the simultaneous application of mean smoothing, median smoothing, and Gaussian smoothing in a single sliding window as an example, for the data points processed by the current sliding window, the mean, median, and Gaussian convolution value of the window data are calculated simultaneously, and then the three data values are averaged again to obtain the final smoothed value output by the enhanced smoothing strategy.
[0065] In this example, for the n data (a1, a2, a3...a n), and perform the following calculation:
[0066] 1) Calculate the mean smoothing value Vmean
[0067]
[0068] 2) Calculate the median smoothing value Vmedian
[0069] Arrange n numbers in ascending order as (r1, r2, r3...r n ), Vmedian is the median of the sorted sequence. If n is an even number, the mean of the two middle numbers is taken as the median of the sequence.
[0070] 3) Calculate the Gaussian smoothing value Vgaus
[0071] Set a Gaussian convolution kernel (w1,w2,w3,...w n ), and convolve with the current window data through the following formula:
[0072]
[0073] 4) Get the target smoothing value V
[0074]
[0075] After the target sliding window traverses and processes the entire sunny reference curve in sequence, a smoothed sunny reference curve is obtained.
[0076] In some embodiments of the present application, the reference curve acquisition method further includes: performing linear interpolation processing on the smoothed sunny reference curve according to the target time accuracy.
[0077] The target time accuracy can be set as required, which can be minute level, second level, etc. For example, in order to meet the need of comparing with real-time data, the data on the sunny day reference curve after smoothing by linear interpolation algorithm can be processed to second level.
[0078] Taking n=8 as an example, FIG4(a) shows the irradiation data in the past 8 days, and FIG4(b) shows the sunny day irradiation reference curve obtained after smoothing and linear interpolation processing based on the data in FIG4(a).
[0079] In a specific embodiment of the present application, Figure 5 As shown in the figure, the process of obtaining the sunny day irradiance reference curve and the sunny day power reference curve is as follows:
[0080] S51, setting the value of n.
[0081] S52, reading the irradiation data and power generation data of the target photovoltaic power station in a preset historical time period from the database.
[0082] S53, verify whether the data is complete and whether there are any abnormal values.
[0083] S54, filtering data within a specified time interval.
[0084] S55, performing time alignment processing on the data of n days.
[0085] S56, selecting the maximum irradiance value of different days at the same time as the sunny day benchmark to obtain a sunny day irradiance benchmark curve; and selecting the maximum power generation power of the photovoltaic module at each time of each day, and then selecting the maximum power generation power of different days at the same time as the sunny day benchmark to obtain a sunny day power benchmark curve.
[0086] S57, using enhanced sliding window smoothing operation to respectively smooth the sunny day irradiation reference curve and the sunny day power reference curve, and then using a linear interpolation algorithm to interpolate the smoothed sunny day irradiation reference curve and the sunny day power reference curve into a second level.
[0087] For some areas where it is sunny most of the time, a relatively accurate sunny day theoretical irradiance and power benchmark curve can be obtained by directly calculating the benchmark curve based on historical data. However, for most areas, due to the frequent changes in weather conditions in a short period of time and large fluctuations during the day, stable sunny days throughout the day are rare. The benchmark curve directly calculated based on historical data may have large fluctuations, which will affect the detection effect. Therefore, for these areas, it is particularly important to adopt a solution based on historical data to fine-tune the output curve of the component clear sky model, in order to obtain more stable and accurate benchmark irradiance and power curves.
[0088] In some embodiments of the present application, the theoretical reference curve is corrected using a sunny day reference curve, including: dividing the sunny day reference curve and the theoretical reference curve into multiple intervals based on time; for each interval, calculating the ratio between the parameter value at each time point on the sunny day reference curve within the interval and the parameter value at each time point on the theoretical reference curve, and obtaining the median of all ratios within the interval; obtaining a total difference coefficient based on multiple medians corresponding to multiple intervals, and using the total difference coefficient to correct the theoretical reference curve.
[0089] Specifically, if the time of the sunny day reference curve and the theoretical reference curve are not aligned, a time alignment operation needs to be performed first to obtain the sunny day reference curve f(x) and the theoretical reference curve g(x) for correction, as shown in Figure 6As shown. Due to the characteristics of sunshine intensity, the irradiance is small in the early morning and late afternoon, and large around noon. The sunny day reference curve and the theoretical reference curve have a large deviation around noon. In order to ensure that the difference coefficient measuring the difference between the two curves can better reflect the difference of the whole day, the design adopts a time-based difference coefficient calculation scheme. The scheme is as follows:
[0090] 1) Define the intervals for measuring differences in segments
[0091] First, see Figure 6 , divide the x-axis into m intervals of equal width, denoted as I1, I2, I3, ..., I m . Each interval is represented by [x i-1 ,x i ], where x0 is the starting point of the x-axis, x m is the end point, and for all i, x i >x i-1 .
[0092] 2) Select data points in each interval
[0093] For each interval I i =[x i-1 ,x i ], select all data points that fall into the interval from the two curves. The two curves are f(x) and g(x), then the interval I i The data points on F are i ={f(x)|x i-1 ≤x≤x i} and G i ={g(x)|x i-1 ≤x≤x i}.
[0094] 3) Calculate the ratio
[0095] For each interval I i , calculate F i Each point in G i For each pair of corresponding points f(x j ) and g(x j ), calculate the ratio r ij =f(x j ) / g(x j ), where j is the jth point in the current interval. If j=1, it means that the current I i The first corresponding point on the two curves of the interval.
[0096] 4) Calculate the interval difference coefficient
[0097] For each interval I i, calculate all ratios r ij The median of i =Median(r ij ). This reflects the central tendency of the relative difference between the two curves within this interval and is insensitive to extreme values. i It can be regarded as a relative difference measure between the two curves in this interval.
[0098] 5) Calculate the total coefficient of variation
[0099] The coefficient of variation D of all intervals i On average, we get the total coefficient of difference D of the two curves over the entire range. total :
[0100]
[0101] Finally, using the total difference coefficient D total Correct the theoretical reference curve, such as multiplying the theoretical reference curve by the total difference coefficient D total , and obtain the target reference curve.
[0102] In one example, the sunny day reference curve, the theoretical reference curve, and the target reference curve are as follows: Figure 7 See Figure 7 The horizontal axis is constant as time, and the vertical axis is divided into irradiation value and power value according to whether the curve is an irradiation curve or a power curve. It should be noted that this application has made fine adjustments to both irradiation and power, and the curves are presented in the same form. Figure 7 is an example of the effect of fine-tuning.
[0103] Figure 7 In the figure, the green curve is the curve calculated by the theoretical model, i.e., the theoretical reference curve; the yellow curve is the reference curve calculated based on historical data (actual data), i.e., the sunny reference curve. It can be seen that there is an obvious deviation between the curve calculated by the theoretical model and the actual curve, but the reference curve based on historical data has a large volatility, which is caused by the large weather fluctuations during the day. In order to obtain a stable sunny reference curve, the yellow curve is used to fine-tune the green curve to obtain the blue curve, i.e., the target reference curve. This curve is more in line with the actual situation of the power station and is more stable. It can more accurately reflect the actual situation of a stable sunny day in the actual power station environment, and is used for subsequent photovoltaic module fault detection with higher accuracy.
[0104] In some embodiments of the present application, before calculating the ratio between the parameter value at each time point on the sunny day reference curve within the interval and the parameter value at each time point on the theoretical reference curve, the interval is also determined to be a target interval, and the parameter value at each time point within the target interval is greater than a preset parameter threshold.
[0105] In this embodiment, the theoretical reference curve is corrected by using the total difference coefficient, including: correcting the theoretical reference curve in each target interval by using the total difference coefficient.
[0106] Specifically, since the actual irradiation and power generation will be at a very small value before sunrise and after sunset, the difference between the sunny day reference curve and the theoretical reference curve in this period (before sunrise and after sunset) will be too large. Therefore, the judgment condition can be set, and when the irradiation and power generation are greater than the corresponding preset thresholds, the subsequent deviation coefficient operation is performed. For example, the preset irradiation threshold can be set to 200, and the preset power generation threshold can be set to 300. If the irradiation values at each time point in the target interval of the sunny day irradiation reference curve and / or the theoretical irradiation reference curve are greater than 200, the subsequent deviation coefficient operation is performed based on the two irradiation reference curves; if the power generation values at each time point in the target interval of the sunny day power reference curve and / or the theoretical power reference curve are greater than 300, the subsequent deviation coefficient operation is performed based on the two power reference curves. In this way, the accuracy of the correction can be improved.
[0107] In some embodiments of the present application, the baseline curve acquisition method also includes: comparing the total difference coefficient with a preset coefficient threshold; if the total difference coefficient is less than or equal to the preset coefficient threshold, executing the step of correcting the theoretical baseline curve using the total difference coefficient; if the total difference coefficient is greater than the preset coefficient threshold, increasing the backtracking time of the historical parameter data, and returning to the step of obtaining the historical parameter data of the target photovoltaic power station.
[0108] Specifically, the preset coefficient threshold can be obtained based on experience or experiments. After obtaining the total difference coefficient, it is necessary to verify the rationality of the total difference coefficient. If the total difference coefficient is too high, higher than the preset coefficient threshold, it indicates that the selected historical parameter data may lack sunny data, then increase the number of backtracking days (such as adding 1 day, 2 days, 3 days, etc., which can be set as needed) and recalculate. When it is verified that the total difference coefficient is less than the preset coefficient threshold, it means that the total difference coefficient is reasonable. At this time, the total difference coefficient is multiplied by each value in the theoretical benchmark curve to obtain the target benchmark curve.
[0109] like Figure 8 As shown in the figure, the process of correcting the theoretical reference curve using the sunny reference curve is as follows:
[0110] S81, set the historical number of days n.
[0111] S82, obtaining a sunny day reference curve based on n days of historical parameter data.
[0112] S83, obtain the theoretical reference curve based on the clear sky model.
[0113] S84, performing time alignment processing on the sunny day reference curve and the theoretical reference curve.
[0114] S85, dividing the sunny day reference curve and the theoretical reference curve into intervals based on time, and obtaining a total difference coefficient according to the sunny day reference curve and the theoretical reference curve for intervals where the irradiation and the power generation power are greater than corresponding preset thresholds.
[0115] S86, check the rationality of the total coefficient of variation.
[0116] If it is lower than the preset coefficient threshold (reasonable), execute step S87; if it is greater than or equal to the preset coefficient threshold (unreasonable), increase the number of retrospective days and return to step S81.
[0117] S87, multiplying the value on the theoretical reference curve by the total difference coefficient to obtain a target reference curve.
[0118] The reference curve acquisition method of the embodiment of the present application has the following technical advantages:
[0119] 1) In view of the instability of the weather, it is difficult to obtain a stable sunny day irradiation and power generation power reference curve for the entire period by relying solely on a single day's historical parameter data. This application uses multi-day historical parameter data in a comprehensive manner, and based on the maximum irradiation value at each time point of each day and the maximum power generation power of multiple photovoltaic strings, a stable and continuous sunny day irradiation reference curve and sunny day power reference curve for the entire period can be constructed;
[0120] 2) Due to the specific properties of some photovoltaic power stations, such as the actual climate environment differences in the photovoltaic power stations, and the differences in the accuracy of the irradiator, the theoretical reference curve obtained based on the traditional clear sky model will deviate from the actual photovoltaic power station clear sky data curve. Therefore, this application fine-tunes the theoretical reference curve obtained by the clear sky model through the clear sky reference curve obtained based on the historical parameter data of the actual operation of the photovoltaic power station, and can obtain a target reference curve that is more in line with the actual situation of the photovoltaic power station. It provides a more reasonable and stable comparison benchmark for subsequent photovoltaic module fault detection, thereby improving the accuracy and reliability of detection.
[0121] 3) Taking into account the natural characteristics that sunlight intensity is lower in the morning and evening and reaches a peak at noon, in order to ensure that the total difference coefficient calculated during fine-tuning can comprehensively and accurately reflect the differences in various time periods throughout the day, this application specifically designs a difference coefficient calculation strategy for different intervals and time periods, which improves the accuracy and representativeness of the curve's full-day difference assessment.
[0122] The present application also proposes a photovoltaic module fault detection method.
[0123] In this embodiment, the photovoltaic module fault detection method includes:
[0124] The target reference curve obtained by the reference curve acquisition method of the above embodiment is used to perform photovoltaic module fault detection.
[0125] Specifically, the data curve currently obtained in real time by the photovoltaic power station can be compared with the target reference curve, such as calculating volatility, smoothness, displacement and other indicators, to determine whether the photovoltaic power station is currently in an abnormal stage. For example, a time window (such as five minutes) is set, and the power data obtained in real time is used to take out the data of the first five minutes of the current moment, and compare it with the five minutes of data on the target reference curve. By calculating the smoothness and displacement of the two curves and comparing them with the threshold, the state of the photovoltaic power station can be determined (such as whether it is in a sandstorm state, whether it is in a fault state, etc.). In addition, real-time judgment can be achieved by setting the sliding window of the window.
[0126] Compared with directly using the reference curve obtained by the clear sky model to detect photovoltaic module faults, the present application uses the target reference curve to detect photovoltaic module faults, which has a higher accuracy.
[0127] Based on the reference curve acquisition method of the above embodiment, the present application proposes a computer-readable storage medium.
[0128] In this embodiment, a computer program is stored on a computer-readable storage medium. When the computer program is executed by a processor, the reference curve acquisition method or photovoltaic component fault detection method of the above embodiment is implemented.
[0129] Fig. 9 It is a structural block diagram of the controller of an embodiment of the present application.
[0130] like Fig. 9 As shown, the electronic device 900 includes: a processor 901 and a memory 903. The processor 901 and the memory 903 are connected, such as through a bus 902. Optionally, the electronic device 900 may also include a transceiver 904. It should be noted that in actual applications, the transceiver 904 is not limited to one, and the structure of the electronic device 900 does not constitute a limitation on the embodiments of the present application.
[0131] Processor 901 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 901 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.
[0132] The bus 902 may include a path to transmit information between the above components. The bus 902 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 902 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0133] The memory 903 is used to store a computer program corresponding to the reference curve acquisition method or photovoltaic module fault detection method of the above-mentioned embodiment of the present application, and the computer program is controlled and executed by the processor 901. The processor 901 is used to execute the computer program stored in the memory 903 to implement the content shown in the above-mentioned method embodiment.
[0134] The electronic device 900 includes but is not limited to mobile terminals such as laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and fixed terminals such as digital TVs and desktop computers. Fig. 9 The electronic device 900 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0135] Corresponding to the reference curve acquisition method of the above embodiment, the present application proposes a reference curve acquisition device.
[0136] Fig.10 It is a structural block diagram of the reference curve acquisition device of an embodiment of the present application.
[0137] like Fig.10 As shown, the reference curve acquisition device 1000 includes: an acquisition module 1100, a processing module 1200 and a correction module 1300. The acquisition module 1100 is used to acquire historical parameter data of a target photovoltaic power station, wherein the historical parameter data includes historical irradiation data and / or historical power generation data; the processing module 1200 is used to obtain a sunny day reference curve of the target photovoltaic power station according to the historical parameter data; the correction module 1300 is used to correct the theoretical reference curve using the sunny day reference curve to obtain a target reference curve, wherein the theoretical reference curve is obtained using a clear sky model, and the target reference curve includes a target irradiation reference curve and / or a target power reference curve.
[0138] In some embodiments of the present application, historical parameter data includes irradiation data within a preset historical time period; a sunny day reference curve of a target photovoltaic power station is obtained based on the historical parameter data, including: dividing the preset historical time period into multiple sub-time periods; for each moment within each sub-time period, taking the maximum value of the irradiation data at that moment within the multiple sub-time periods as the target irradiation value at that moment; and obtaining a sunny day irradiation reference curve based on the target irradiation value.
[0139] In some embodiments of the present application, obtaining a sunny day irradiation reference curve according to a target irradiation value includes: determining the sunny day irradiation reference curve according to all obtained moments and their corresponding target irradiation values.
[0140] In some embodiments of the present application, the historical parameter data includes power generation data within a preset historical time period, and the target photovoltaic power station includes multiple photovoltaic strings; a sunny day reference curve of the target photovoltaic power station is obtained based on the historical parameter data, including: dividing the preset historical time period into multiple sub-time periods; for each moment in each sub-time period, the maximum value of the power generation data of multiple photovoltaic strings in the sub-time period at that moment is used as the first target power generation value of the sub-time period at that moment, and for each moment in the multiple sub-time periods, the maximum value of the first target power generation value at that moment in the preset historical time period is used as the second target power generation value at that moment; and the sunny day power reference curve is obtained according to the second target power generation value.
[0141] In some embodiments of the present application, obtaining a sunny day power reference curve according to the second target power generation value includes: determining the sunny day power reference curve according to all obtained moments and their corresponding second target power generation values.
[0142] In some embodiments of the present application, the theoretical reference curve is corrected using a sunny day reference curve, including: dividing the sunny day reference curve and the theoretical reference curve into multiple intervals based on time; for each interval, calculating the ratio between the parameter value at each time point on the sunny day reference curve within the interval and the parameter value at each time point on the theoretical reference curve, and obtaining the median of all ratios within the interval; obtaining a total difference coefficient based on multiple medians corresponding to multiple intervals, and using the total difference coefficient to correct the theoretical reference curve.
[0143] In some embodiments of the present application, before calculating the ratio between the parameter value at each time point on the sunny day reference curve within the interval and the parameter value at each time point on the theoretical reference curve, the processing module 1200 is also used to: determine that the interval is a target interval, and the parameter value at each time point within the target interval is greater than a preset parameter threshold; wherein the theoretical reference curve is corrected using the total difference coefficient, including: correcting the theoretical reference curve within each target interval using the total difference coefficient.
[0144] In some embodiments of the present application, the processing module 1200 is further used to compare the total difference coefficient with a preset coefficient threshold. The correction module 1300 is used to correct the theoretical reference curve using the total difference coefficient when the total difference coefficient is less than or equal to the preset coefficient threshold. If the total difference coefficient is greater than the preset coefficient threshold, the processing module 1200 further increases the backtracking time of the historical parameter data, and the acquisition module 1100 further acquires the historical parameter data of the target photovoltaic power station based on the increased backtracking time.
[0145] In the embodiments of the present application, for other specific implementations of the reference curve acquisition device 1000, reference may be made to the specific implementations of the reference curve acquisition method in the above-mentioned embodiments of the present invention.
[0146] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0147] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0148] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0149] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.
[0150] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0151] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0152] In the present application, unless otherwise clearly specified and limited, a first feature being “above” or “below” a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being “above”, “above”, and “above” a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being “below”, “below”, and “below” a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.
[0153] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A method for obtaining a reference curve, characterized in that: include: Acquiring historical parameter data of a target photovoltaic power station, wherein the historical parameter data includes historical irradiation data and / or historical power generation data; Obtaining a sunny day reference curve of the target photovoltaic power station according to the historical parameter data; The theoretical reference curve is corrected using the clear sky reference curve to obtain a target reference curve, wherein the theoretical reference curve is obtained using a clear sky model, and the target reference curve includes a target irradiation reference curve and / or a target power reference curve.
2. The method for obtaining a reference curve according to claim 1, characterized in that: The historical parameter data includes irradiation data within a preset historical time period; and obtaining the sunny day reference curve of the target photovoltaic power station according to the historical parameter data includes: Dividing the preset historical time period into a plurality of sub-time periods; For each moment in each sub-time period, taking the maximum value of the irradiation data at that moment in a plurality of the sub-time periods as the target irradiation value at that moment; A sunny day irradiance reference curve is obtained according to the target irradiance value.
3. The method for obtaining a reference curve according to claim 2, characterized in that: The step of obtaining a sunny day irradiance reference curve according to the target irradiance value comprises: The sunny day irradiation reference curve is determined according to all obtained moments and their corresponding target irradiation values.
4. The method for obtaining a reference curve according to claim 1, characterized in that: The historical parameter data includes power generation data within a preset historical time period, and the target photovoltaic power station includes a plurality of photovoltaic strings; and obtaining a sunny day reference curve of the target photovoltaic power station according to the historical parameter data includes: Dividing the preset historical time period into a plurality of sub-time periods; For each moment in each sub-time period, the maximum value of the power generation data of the plurality of photovoltaic strings in the sub-time period at the moment is used as the first target power generation value of the sub-time period at the moment, and the maximum value of the first target power generation values in the plurality of sub-time periods at the moment is used as the second target power generation value at the moment; A sunny day power reference curve is obtained according to the second target power generation value.
5. The method for obtaining a reference curve according to claim 4, characterized in that: The obtaining of a sunny day power reference curve according to the second target power generation value comprises: The sunny day power reference curve is determined according to all the obtained moments and their corresponding second target power generation values.
6. The method for obtaining a reference curve according to claim 1, characterized in that: The method of using the sunny day reference curve to correct the theoretical reference curve includes: Dividing the sunny day reference curve and the theoretical reference curve into a plurality of intervals based on time; For each interval, calculate the ratio between the parameter value at each time point on the sunny reference curve in the interval and the parameter value at each time point on the theoretical reference curve in the interval, and obtain the median of all ratios in the interval; A total coefficient of difference is obtained according to a plurality of medians corresponding to the plurality of intervals, and the theoretical reference curve is corrected using the total coefficient of difference.
7. The method for obtaining a reference curve according to claim 6, characterized in that: Before calculating the ratio between the parameter value at each time point on the sunny reference curve within the interval and the parameter value at each time point on the theoretical reference curve, the method further includes: Determining that the interval is a target interval, and the parameter value at each time point in the target interval is greater than a preset parameter threshold; Wherein, the use of the total difference coefficient to correct the theoretical reference curve includes: The total difference coefficient is used to correct the theoretical reference curve within each target interval.
8. The method for obtaining a reference curve according to claim 6 or 7, characterized in that: The method further comprises: comparing the total difference coefficient with a preset coefficient threshold; If the total difference coefficient is less than or equal to the preset coefficient threshold, performing the step of correcting the theoretical reference curve using the total difference coefficient; If the total difference coefficient is greater than the preset coefficient threshold, the backtracking time of the historical parameter data is increased, and the process returns to the step of obtaining the historical parameter data of the target photovoltaic power station.
9. A reference curve acquisition device, characterized in that: include: An acquisition module, used to acquire historical parameter data of a target photovoltaic power station, wherein the historical parameter data includes historical irradiation data and / or historical power generation data; A processing module, configured to obtain a sunny day reference curve of the target photovoltaic power station according to the historical parameter data; The correction module is used to correct the theoretical reference curve using the clear sky reference curve to obtain a target reference curve, wherein the theoretical reference curve is obtained using a clear sky model, and the target reference curve includes a target irradiation reference curve and / or a target power reference curve.
10. A photovoltaic module fault detection method, characterized in that: include: Photovoltaic module fault detection is performed using the target reference curve obtained by the reference curve acquisition method according to any one of claims 1 to 8.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the reference curve acquisition method according to any one of claims 1 to 8, or the photovoltaic component fault detection method according to claim 10 is implemented.
12. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the reference curve acquisition method according to any one of claims 1 to 8, or the photovoltaic component fault detection method according to claim 10 is implemented.
Citation Information
Cited By
Remote data acquisition and management platform for photovoltaic power station
CN119862522A
