Power generation efficiency detection method and device and storage medium

Abstract

The embodiment of the invention provides a power generation efficiency detection method and device and a storage medium. In the embodiment of the invention, the curve characteristics of the power time sequence curve of the photovoltaic power generation unit can reflect the power generation efficiency characteristics of the photovoltaic power generation unit, and the curve characteristics of the power time sequence curve of the photovoltaic power generation unit are extracted to obtain the curve characteristics of the power time sequence curve of the photovoltaic power generation unit; the quantification of the geometric morphology of the power time sequence curve of the photovoltaic power generation unit is realized; and the power generation efficiency of the plurality of photovoltaic power generation units is evaluated according to the power time sequence curves corresponding to the plurality of photovoltaic power generation units, so that automatic detection of the power generation efficiency of the photovoltaic power generation units is realized, manual inspection of the photovoltaic power generation units is not needed, the detection time consumption of the power generation efficiency of the photovoltaic power generation units can be reduced, and the power generation efficiency detection speed is improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method, device, and storage medium for detecting power generation efficiency. Background Art

[0002] Photovoltaic power generation is a technology that directly converts light energy into electrical energy using the photovoltaic effect at the semiconductor interface. It mainly consists of three major parts: photovoltaic cells, controllers, and inverters, and the main components are composed of electronic components. After the photovoltaic cell monomers are connected in series and parallel and encapsulated, a photovoltaic array is formed.

[0003] Since the photovoltaic array is exposed outdoors all year round, the photovoltaic array is easily affected by the environment and generates abnormalities. The power generation efficiency of the photovoltaic array with abnormalities is low, and it may even be unable to generate electricity normally. The quality of the power generation efficiency of the photovoltaic array can, to a certain extent, reflect whether the photovoltaic array is abnormal. Therefore, detecting the quality of the power generation efficiency of the photovoltaic array or even the photovoltaic station can provide a basis for determining whether the photovoltaic array is abnormal.

[0004] In the traditional solution, the most common way to solve the problem of reduced photovoltaic power generation efficiency is through manual inspection. Workers screen out the photovoltaic arrays with low power generation efficiency from the monitoring system. This manual inspection method has a huge workload and takes a long time for power generation efficiency detection. Summary of the Invention

[0005] Multiple aspects of this application provide a method, device, and storage medium for detecting power generation efficiency to improve the speed of power generation efficiency detection.

[0006] An embodiment of this application provides a method for detecting power generation efficiency, including:

[0007] Obtain multiple power time series curves of multiple photovoltaic power generation units; each photovoltaic power generation unit corresponds to at least one power time series curve;

[0008] Extract curve features from the multiple power time series curves to obtain the curve features of the multiple power time series curves;

[0009] According to the curve features of the multiple power time series curves, perform power generation efficiency detection on the multiple photovoltaic power generation units.

[0010] An embodiment of this application also provides a method for detecting power generation efficiency, which is applicable to a cloud server. The method includes:

[0011] In response to a request to call a target service, determine the processing resources corresponding to the target service;

[0012] Use the processing resources corresponding to the target service to execute the steps in the above method for detecting power generation efficiency.

[0013] An embodiment of the present application further provides an electronic device, including: a memory and a processor; wherein, the memory is used for storing a computer program;

[0014] The processor is coupled to the memory and is used for executing the computer program to execute the steps in the above-mentioned power generation efficiency detection methods.

[0015] An embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which when executed by one or more processors, cause the one or more processors to execute the steps in the above-mentioned power generation efficiency detection methods.

[0016] In the embodiment of the present application, the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the characteristics of the power generation efficiency of the photovoltaic power generation unit. By extracting the curve characteristics of the power time series curve of the photovoltaic power generation unit, the curve characteristics of the power time series curve of the photovoltaic power generation unit are obtained, and the geometric shape of the power time series curve of the photovoltaic power generation unit is quantified; and according to the power time series curves corresponding to multiple photovoltaic power generation units, the power generation efficiencies of the multiple photovoltaic power generation units are evaluated, realizing the automatic detection of the power generation efficiency of the photovoltaic power generation unit, without manual inspection of the photovoltaic power generation unit, which can reduce the detection time of the power generation efficiency of the photovoltaic power generation unit and improve the power generation efficiency detection speed. Description of the Drawings

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0018] Figure 1 is a schematic structural diagram of a computing system provided by an embodiment of the present application;

[0019] Figure 2 is an equivalent circuit diagram of a single photovoltaic cell provided by an embodiment of the present application;

[0020] Figure 3 is a schematic diagram of the power time series curve of a photovoltaic power generation unit in a normal state provided by an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of the power time series curve of a photovoltaic power generation unit in an abnormal state provided by an embodiment of the present application;

[0022] Figure 5 is a schematic diagram of a general curve provided by an embodiment of the present application;

[0023] Figure 6 is a schematic diagram of the osculating circle of a general curve provided by an embodiment of the present application;

[0024] Figure 7 Schematic diagram of the extreme value of the power time series curve provided by the embodiment of the present application;

[0025] Figure 8 and Figure 9 Schematic diagram of the flow of the power generation efficiency detection method provided by the embodiment of the present application;

[0026] Figure 10 Schematic diagram of the power time series curve of some photovoltaic sites provided by the embodiment of the present application;

[0027] Figure 11 Schematic diagram of the power time series curve of the photovoltaic sites with good power generation efficiency classified by the embodiment of the present application;

[0028] Figure 12 Schematic diagram of the power time series curve of the photovoltaic sites with poor power generation efficiency classified by the embodiment of the present application;

[0029] Figure 13 Schematic diagram of the structure of the electronic device provided by the embodiment of the present application. Detailed implementation manners

[0030] To make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0031] In order to improve the detection speed of power generation efficiency, in some embodiments of the present application, by using the characteristic that the curve feature of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit, the curve feature of the power time series curve of the photovoltaic power generation unit is extracted to obtain the curve feature of the power time series curve of the photovoltaic power generation unit, realizing the quantification of the geometric shape of the power time series curve of the photovoltaic power generation unit; and according to the power time series curves corresponding to multiple photovoltaic power generation units, the power generation efficiency of multiple photovoltaic power generation units is evaluated, realizing the automatic detection of the power generation efficiency of the photovoltaic power generation unit, eliminating the need for manual inspection of the photovoltaic power generation unit, reducing the detection time of the power generation efficiency of the photovoltaic power generation unit, and improving the detection speed of power generation efficiency.

[0032] The following will describe in detail the technical solutions provided by each embodiment of the present application with reference to the drawings.

[0033] It should be noted that the same reference numerals represent the same object in the following drawings and embodiments. Therefore, once an object is defined in one drawing or embodiment, it does not need to be further discussed in the subsequent drawings and embodiments.

[0034] Figure 1 This is a schematic structural diagram of the power generation efficiency detection system provided by the embodiments of the present application. As Figure 1 shown, the power generation efficiency detection system includes: a plurality of photovoltaic power generation units 10 and a computing device 20. The term "plurality" means two or more.

[0035] The photovoltaic power generation unit can directly convert solar energy into electrical energy by using a photovoltaic array made based on the principle of the photovoltaic effect. A single photovoltaic cell is the smallest unit for photovoltaic conversion. After the single photovoltaic cells are connected in series and parallel and encapsulated, a photovoltaic array is formed. According to Figure 2 the equivalent circuit diagram of the single photovoltaic cell shown, when the solar cell irradiated by light is connected to a load R 0 , the photocurrent I flows through the load R 0 and forms a voltage U across the load R 0 , and at the same time generates an output power P externally.

[0036] Among them, the photovoltaic power generation unit 10 is the smallest detection unit for detecting the high and low power generation efficiency in the embodiments of the present application, and may include one or more photovoltaic arrays. The term "plurality" means two or more. One photovoltaic power generation unit 10 may be all the photovoltaic arrays of a photovoltaic site, or may be part of the photovoltaic arrays of a photovoltaic site. For example, it may be a row or a column of photovoltaic arrays of a photovoltaic site, or a photovoltaic array matrix composed of part of the rows and part of the columns of photovoltaic arrays of a photovoltaic site. Figure 1 Only the case where the photovoltaic power generation unit 10 includes two photovoltaic arrays is illustrated in

[0037] but it does not constitute a limitation. Among them, a photovoltaic array refers to a photovoltaic cell array formed after the single photovoltaic cells are connected in series and parallel and encapsulated.

[0038] In this embodiment, the computing device 20 refers to a computer device capable of data processing, which can have the ability to undertake and guarantee services. The computing device 20 can be a single server device, or a cloudified server array, or a virtual machine (VM) running in a cloudified server array. Additionally, the computing device 20 can also refer to other computing devices with corresponding service capabilities, such as terminal devices (running service programs) like computers or Internet of Things (IoT) devices, etc.

[0039] The inventors of this application have found through research that under a determined sunlight intensity and temperature, the output voltage and output current of a photovoltaic power generation unit follow the current-voltage (I-V) characteristic relationship. During the daily power generation process, the external environment is constantly changing, and the output power of the photovoltaic power generation unit is also constantly changing. As Figure 3 shown, when the photovoltaic power generation unit is in a normal working state, its output power changes continuously with the change of the external environment. When there is no light irradiation at night, the photovoltaic power generation unit has no power output. After sunrise, as the light gradually increases, the output power of the photovoltaic power generation unit also continuously increases and reaches the maximum value in the afternoon, and then continuously decreases. After sunset, the light irradiation tends to 0 again, and the output power of the photovoltaic power generation unit also tends to 0. Therefore, when the photovoltaic power generation unit is in a normal working state, its power has a certain corresponding relationship with time. In the embodiment of this application, the relationship curve of the photovoltaic power changing with time is defined as the power time series curve. For example, the relationship between the photovoltaic power and time is called the power-time (P-T) curve.

[0040] According to Figure 3 the power time series curve shown, the power time series curve of the photovoltaic power generation unit 10 has strong nonlinearity. When the light is sufficient and the photovoltaic power generation unit 10 is normal, the geometric shape of the photovoltaic power generation unit 10 is approximately a downward-opening horseshoe-shaped parabola. The power corresponding to the vertex of this parabola is the maximum output power of the photovoltaic power generation unit 10 on that day.

[0041] However, when there are changes in the external environment of the photovoltaic power generation unit 10 (such as rainy weather or shading of the photovoltaic power generation unit 10), or when the photovoltaic power generation unit 10 itself has abnormalities (such as short circuit or aging of the photovoltaic power generation unit 10), the power generation efficiency of the photovoltaic power generation unit 10 is low, and the power time series curve of the photovoltaic power generation unit 10 is complex and variable, and the geometric shape of its curve significantly deviates from Figure 3 the power time series curve in the normal state shown, that is, it seriously deviates from Figure 3 the plump horseshoe-shaped parabola shown. For example, Figure 4As shown by the power time-sequence curve of the photovoltaic power generation unit with low power generation efficiency, the change of the power of the photovoltaic power generation unit with low power generation efficiency over time is irregular and complex, and is significantly different from the shape of the power time-sequence curve of the photovoltaic power generation unit in the normal state.

[0042] Based on the above analysis of the power time-sequence curve of the photovoltaic power generation unit in the normal power generation state and the power time-sequence curve of the photovoltaic power generation unit with low power generation efficiency, it can be seen that the power time-sequence curves of the photovoltaic power generation unit with normal power generation efficiency and the photovoltaic power generation unit with low power generation efficiency are completely different. Therefore, to a certain extent, the power time-sequence curve of the photovoltaic power generation unit can reflect the level of power generation efficiency of the photovoltaic power generation unit.

[0043] Based on this, in the embodiment of the present application, in order to detect the level of power generation efficiency of the photovoltaic power generation unit, the calculation device 20 can obtain multiple power time-sequence curves of multiple photovoltaic power generation units 10. Among them, the multiple photovoltaic power generation units 10 are the photovoltaic power generation units whose power generation efficiency is to be detected. Each photovoltaic power generation unit 10 corresponds to at least one power time-sequence curve. Optionally, each photovoltaic power generation unit 10 can correspond to one power time-sequence curve.

[0044] In some embodiments, a power acquisition device ( Figure 1 not shown in the figure) can be used to collect the power time-sequence data of each photovoltaic power generation unit 10 within the sampling period. Each power data corresponds to a time point in the sampling period. In the embodiment of the present application, the specific value of the sampling period is not limited. Optionally, the sampling period can be 1 day or multiple days. Multiple days means 2 days or more. Generally, the sampling period can be 1 day. Further, the power acquisition device can send the power time-sequence data of the photovoltaic power generation unit 10 within the sampling period to the calculation device 20. Or, the power acquisition device itself can also be implemented as the calculation device 20.

[0045] For the calculation device 20, it can determine the power time-sequence curve of the photovoltaic power generation unit 10 according to the power time-sequence data of the photovoltaic power generation unit 10 within the sampling period. Among them, the power time-sequence data is discretized sampling data, including a series of discretized power sampling points. Each power sampling point includes timestamp information and the power of the photovoltaic power generation unit corresponding to the timestamp information. Correspondingly, the power time-sequence data of the photovoltaic power generation unit within the sampling period can be connected by dotted lines to obtain the power time-sequence curve of the photovoltaic power generation unit. Or, the power time-sequence data of the photovoltaic power generation unit within the sampling period can be fitted with a smooth curve to obtain the power time-sequence curve of the photovoltaic power generation unit. Among them, the data point corresponding to the timestamp information of the power time-sequence data on the power time-sequence curve is the power sampling point on the power time-sequence curve. For example, Figure 3 if the power time-sequence data includes: the power at 6:00, the power at 9:00, the power at 12:00, and the power at 15:00, etc., thenFigure 3 The power sampling points on the shown power time sequence curve include: the data points on the power time sequence curve at 6:00, the data points on the power time sequence curve at 9:00, the data points on the power time sequence curve at 12:00, the data points on the power time sequence curve at 15:00, etc.

[0046] Further, the computing device 20 can extract the curve features of the power time sequence curve to obtain the curve features of each power time sequence curve. The curve features of the power time sequence curve are the features related to the shape of the power time sequence curve, and to a certain extent, these curve features can reflect the power generation efficiency of the photovoltaic power generation unit 10 corresponding to the power time sequence curve.

[0047] Combined with Figure 3 and Figure 4 the power time sequence curves in different power generation efficiency states shown, it can be seen that for a photovoltaic power generation unit with sufficient light and good state, its power generation efficiency is relatively high, the corresponding power time sequence curve is relatively smooth, and the average curvature of the power time sequence curve is relatively small. While a photovoltaic power generation unit that is frequently interfered by external environmental factors and / or has internal abnormalities has a relatively low power generation efficiency, the corresponding power time sequence curve is complex and changeable, and the average curvature is relatively large. Based on this, the curve features of the power time sequence curve can include: the average curvature of the power time sequence curve. Among them, the curvature is an index to measure the degree of curve bending.

[0048] Based on this, for any power time sequence curve P(t), the computing device 20 can extract the curvature of the power sampling points on the power time sequence curve P(t); and calculate the average curvature of the power time sequence curve according to the curvature of the power sampling points on the power time sequence curve, and use it as the curve feature of the power time sequence curve P(t).

[0049] Among them, for a circle, the larger the radius of the circle, the flatter the circumference, and the smaller the degree of bending, that is, the smaller the curvature. Geometrically, the reciprocal of the radius r of the circle is defined as the curvature of the circumference, that is, the curvature of the circle is:

[0050]

[0051] In formula (1), κ 0 represents the curvature of the circle; r represents the radius of the circle.

[0052] Under this definition, a straight line is a circle with an infinite radius, and its curvature κ 1 is:

[0053]

[0054] Each point on the circumference has the same radius, so the curvature of each point is equal. For a general curve, such as Figure 5As shown by curves 1 - 3, the curves are sometimes straight and sometimes curved, and the curvatures of the points on the curves are not the same. Therefore, the curvature of a circle can be extended to an ordinary curve. In some embodiments, the curvature of the osculating circle at each point on the curve can be used as the curvature of the corresponding point on the curve. For example, as Figure 6 shown, the osculating circles at points A, B, and C on the curve are circles with radii r1, r2, and r3 respectively, then the curvature of point A is 1 / r1; the curvature of point B is 1 / r2; the curvature of point C is 1 / r3.

[0055] Among them, assuming that the analytical expression of the curve is f(x), then at x 0 the radius of the osculating circle is:

[0056]

[0057] In formula (3), r(x 0 ) is the radius of the osculating circle of f(x) at x 0 , f'(x 0 ) represents the first derivative of f(x) at x 0 , f”(x 0 ) represents the second derivative of f(x) at x 0 . Among them, the second derivative of f(x) at x 0 is not 0.

[0058] Correspondingly, the curvature κ(x 0 ) of f(x) at x 0 can be expressed as:

[0059]

[0060] Based on the above method for representing the curvature κ(x 0 ) of the curve f(x) at x 0 , in this embodiment, the computing device 20 can calculate the radius of the osculating circle of the power sampling points on the power timing curve P(t).

[0061] In practical applications, the collected power time-series data is discretized sampled data. Then, the first-order difference of the power time-series curve can be used to represent the first derivative of the power time-series curve, and the second-order difference can be used to represent the second derivative of the power time-series curve. Correspondingly, the computing device 20 can calculate the first-order difference and the second-order difference of the power sampling points on the power time-series curve P(t) according to the power and time corresponding to the power sampling points on the power time-series curve P(t); and calculate the radius of the osculating circle of the power sampling points on the power time-series curve P(t) according to the first-order difference and the second-order difference of the power sampling points on the power time-series curve P(t). Specifically, the first-order difference of the power sampling points on the power time-series curve P(t) can be used as the first derivative at the corresponding time; and the second-order difference of the power sampling points on the power time-series curve P(t) can be used as the second derivative at the corresponding time, and substitute them into the above formula (6) for calculation to obtain the radius of the osculating circle of the power sampling points on the power time-series curve P(t). Further, the reciprocal of the radius of the osculating circle of the power sampling points on the power time-series curve P(t) can be used as the curvature of the power sampling points on the power time-series curve P(t).

[0062] Correspondingly, the power time-series curve P(t) at time t 0 The curvature κ(t 0 ) can be expressed as:

[0063]

[0064] In formula (5), ΔP(t 0 ) represents the first-order difference of the power time-series curve at time t 0 ; Δ(ΔP(t 0 )) represents the second-order difference of the power time-series curve at time t 0 .

[0065] Further, the average curvature of the power time-series curve can be calculated according to the curvature of the power sampling points on the power time-series curve P(t), and used as the curve feature of the power time-series curve P(t). Specifically, the mean value of the curvatures of the power sampling points on the power time-series curve P(t) can be calculated as the average curvature of the power time-series curve P(t). Correspondingly, the average curvature of the power time-series curve P(t) can be expressed as:

[0066]

[0067] In formula (6), represents the average curvature of the power time-series curve P(t); m represents the total number of sampling points on the power time-series curve P(t). κ(t i ) represents the curvature of the power time-series curve P(t) at time t i , i = 0, 1, 2,..., m.

[0068] In some other embodiments, in combination with Figure 3 and Figure 4 From the power time - series curves shown under different power generation efficiency states, it can be seen that for a photovoltaic power generation unit with sufficient light and good condition, its power generation efficiency is relatively high, and the corresponding power time - series curve is relatively smooth, showing a convex - up characteristic, and the frequency of the concavity - convexity change of the curve is relatively low. While a photovoltaic power generation unit that is frequently disturbed by external environmental factors and / or has internal abnormalities has a relatively low power generation efficiency, and the corresponding power time - series curve is complex and changeable, and the frequency of the concavity - convexity change of the curve varies. Based on this, the curve characteristics of the power time - series curve may include: the frequency of the concavity - convexity change of the power time - series curve.

[0069] Correspondingly, the computing device 20 can extract the characterization information of the frequency of the concavity - convexity change of the power time - series curve P(t) from the power time - series curve P(t) as the curve characteristics of the power time - series curve P(t). Among them, the frequency of the concavity - convexity change of the power time - series curve of a photovoltaic power generation unit with sufficient light and good condition is low; for a photovoltaic power generation unit that is frequently disturbed by external environmental factors and / or has internal abnormalities, the frequency of the concavity - convexity change of its power time - series curve is high.

[0070] Among them, the characterization information of the frequency of the concavity - convexity change of the power time - series curve P(t) refers to the information that can be used to reflect the frequency of the concavity - convexity change of the power time - series curve P(t).

[0071] In some embodiments, since the extreme value of the curve can be used to determine the concavity - convexity of the curve, and the change frequency of the extreme value of the curve can reflect the change frequency of the concavity - convexity of the curve, therefore, the change frequency of the extreme value of the power time - series curve P(t) can be used as the characterization information of the frequency of the concavity - convexity change of the power time - series curve P(t).

[0072] Correspondingly, the computing device 20 can calculate the extreme values of the power time - series curve P(t), and calculate the average time interval between the extreme values of the power time - series curve P(t) according to the time interval between any two adjacent extreme values; then, the reciprocal of the average time interval between the extreme values of the power time - series curve P(t) can be used as the change frequency of the extreme values of the power time - series curve P(t). Among them, the change frequency of the extreme values of the power time - series curve P(t) is the characterization information of the frequency of the concavity - convexity change of the power time - series curve P(t).

[0073] For example, as Figure 7 shown, the extreme values of the power time - series curve P(t) are the points corresponding to times t1, t2, t3, and t4 respectively, and the average time interval between the extreme values of the power time - series curve P(t) can be expressed as: Correspondingly, the change frequency of the extreme values of the power time - series curve P(t) can be That is, the characterization information of the frequency of the concavity - convexity change of the power time - series curve P(t) is the change frequency of the extreme values of the power time - series curve P(t)

[0074] In some other embodiments, since the extreme values of a curve can be used to determine the concavity and convexity of the curve, the change frequency of the extreme values of the curve can reflect the change frequency of the concavity and convexity of the curve, and the number of extreme values of the curve determines the number of folds of the curve. In this embodiment, a curve segment between two adjacent extreme values of the curve is one fold. Among them, a curve with a high change frequency of concavity and convexity has a larger number of folds; a curve with a low change frequency of concavity and convexity has a smaller number of folds. The fewer the number of folds of the curve, the smoother the curve and the lower the change frequency of concavity and convexity. Based on this, the number of folds (Folds) of the power time series curve P(t) can be used to represent the characterization information of the change frequency of the concavity and convexity of the power time series curve P(t).

[0075] Correspondingly, the computing device 20 can calculate the extreme values of the power time series curve P(t), and determine the number of folds of the power time series curve P(t) according to the number of extreme values of the calculated power time series curve P(t), as the characterization information of the change frequency of the concavity and convexity of the power time series curve P(t). Among them, a curve segment between two adjacent extreme values is one fold of the power time series curve P(t).

[0076] In still some other embodiments, combining Figure 3 and Figure 4 the power time series curves shown, it can be known that for a photovoltaic power generation unit with sufficient light and good conditions, its power generation efficiency is relatively high, and the integral area of the power time series curve in the corresponding target time period is relatively large; while a photovoltaic power generation unit that is frequently interfered by external environmental factors and / or has internal abnormalities has a low power generation efficiency, and the integral area of the corresponding power time series curve in the corresponding time period is relatively small.

[0077] Since the physical meaning of the power time series curve is the power generation power of the photovoltaic power generation unit at each moment, therefore, the integral area of the power time series curve P(t) in the corresponding target time period can represent the cumulative power of the photovoltaic power generation unit in the target time period. Among them, the target time period is the sampling time period corresponding to the power time series curve P(t). For example, the target time period can be the time period from sunrise to sunset in a day, such as the time period from 6 am to 8 pm, etc. Correspondingly, the cumulative power of the photovoltaic power generation unit in the target time period can be represented by the integral area of the power time series curve P(t) of this photovoltaic power generation unit in the target time period, that is, the cumulative power of the photovoltaic power generation unit in the target time period can be expressed as:

[0078]

[0079] In Equation (7), P tIt represents the cumulative power of the photovoltaic power generation unit over the target duration; t1 and t2 respectively represent the start time and end time of the target duration corresponding to the power time series curve P(t). Generally, t1 represents the sunrise time and t2 represents the sunset time. In the embodiments of the present application, the target durations corresponding to the multiple power time series curves of the plurality of photovoltaic power generation units 10 obtained are equal, and the start time and end time of the target duration are also the same.

[0080] In an ideal state, we hope that the cumulative power generation per day is as large as possible. Combining Figure 3 and Figure 4 the power time series curves shown, it can be seen that for a photovoltaic power generation unit with sufficient light and good condition, its power generation efficiency is relatively high, and the cumulative power generation per day is large, so the integral area of the power time series curve over the corresponding target duration is relatively large; while a photovoltaic power generation unit that is frequently interfered by external environmental factors and / or has internal abnormalities has a low power generation efficiency, a small cumulative power generation per day, and the integral area of the corresponding power time series curve over the corresponding duration is small. Therefore, to a certain extent, the integral area of the power time series curve of the photovoltaic power generation unit over the target duration can reflect the power generation efficiency of the photovoltaic power generation unit. Based on this, the curve characteristics of the power time series curve may include: the integral area of the power time series curve over the target duration.

[0081] Correspondingly, the computing device 20 can calculate the integral area of the power time series curve P(t) over the target duration as the curve characteristic of the power time series curve P(t). Among them, the target duration is the sampling duration of the power time series curve P(t); the start and end times of the target duration are the sampling start and end times of the power time series curve P(t).

[0082] The curve characteristics of the power time series curve P(t) shown in the above embodiments are only for illustrative purposes and do not constitute a limitation. In the embodiments of the present application, the curve characteristics of the power time series curve P(t) may include at least one of: the average curvature of the power time series curve P(t), the characterization information of the frequency of concavity and convexity change of the power time series curve P(t), and the integral area of the power time series curve P(t) over the target duration. Preferably, the curve characteristics of the power time series curve P(t) may include multiple of the average curvature of the power time series curve P(t), the characterization information of the frequency of concavity and convexity change of the power time series curve P(t), and the integral area of the power time series curve P(t) over the target duration. Multiple means two or more than two. For example, the curve characteristics of the power time series curve P(t) may include: the average curvature of the power time series curve P(t), the characterization information of the frequency of concavity and convexity change of the power time series curve P(t), and the integral area of the power time series curve P(t) over the target duration, etc.

[0083] Since the curve characteristics of the power time series curve P(t) of the photovoltaic power generation unit 10 can reflect the power generation efficiency of the photovoltaic power generation unit 10, based on this, the computing device 20 can detect the power generation efficiency of multiple photovoltaic power generation units 10 according to the curve characteristics of multiple power time series curves corresponding to the multiple photovoltaic power generation units 10. It should be noted that in the embodiments of the present application, detecting the power generation efficiency of the photovoltaic power generation unit mainly performs a quality assessment on the power generation efficiency of the photovoltaic power generation unit, and evaluates the high or low, good or bad of the power generation efficiency of the photovoltaic power generation unit.

[0084] In this embodiment, by using the characteristic that the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit, the curve characteristics of the power time series curve of the photovoltaic power generation unit are extracted to obtain the curve characteristics of the power time series curve of the photovoltaic power generation unit, realizing the quantification of the geometric shape of the power time series curve of the photovoltaic power generation unit; and according to the power time series curves corresponding to multiple photovoltaic power generation units, the power generation efficiency of multiple photovoltaic power generation units is evaluated, realizing the automatic detection of the power generation efficiency of the photovoltaic power generation unit, without the need for manual inspection of the photovoltaic power generation unit, which can reduce the detection time of the power generation efficiency of the photovoltaic power generation unit and provide the power generation efficiency detection speed.

[0085] On the other hand, when the artificial inspection method is used to check the power generation efficiency of the photovoltaic power generation unit, the inspection workload is large, and it is easy to cause missed inspections or even misinspections. The embodiments of the present application use the characteristic that the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit to realize the automatic detection of the power generation efficiency of the photovoltaic power generation unit. Compared with the artificial inspection method, the missed inspection probability of the photovoltaic power generation unit can also be reduced. Since the automatic detection reduces the error of human factors, the accuracy of the power generation efficiency detection can also be improved.

[0086] In addition, the embodiments of the present application use the characteristic that the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit to realize the automatic detection of the power generation efficiency of the photovoltaic power generation unit. The requirements for data collection are simple, do not require a large amount of historical time series data, do not need to label the quality of the power generation efficiency of the historical time series data, and do not require meteorological data, which can reduce the data collection cost.

[0087] In some embodiments of the present application, when the computing device 20 detects the power generation efficiency of multiple photovoltaic power generation units 10 according to the curve characteristics of multiple power time series curves corresponding to the multiple photovoltaic power generation units 10, the computing device 20 can determine the efficiency rank-sum ratio (Rank-Sum Ratio, RSR) of the multiple photovoltaic power generation units 10 according to the curve characteristics of the multiple power time series curves corresponding to the multiple photovoltaic power generation units 10.

[0088] Among them, the rank sum ratio is a comprehensive analysis method that can be used to evaluate the comprehensive level of multiple indicators. Its essential principle is to utilize the RSR value information for various mathematical calculations, and the RSR value ranges from 0 to 1. Generally, the larger the RSR value, the better the comprehensive level. In the embodiments of the present application, the larger the value of the efficiency rank sum ratio, the higher the power generation efficiency.

[0089] In the RSR comprehensive evaluation method, the benefit-type indicators can be ranked from small to large, and the cost-type indicators can be ranked from large to small. Then, the rank sum ratio is calculated, and finally, regression is statistically analyzed and ranked in grades. The RSR value is used to directly rank or rank in grades the pros and cons of the evaluation object, so as to make a comprehensive evaluation of the evaluation object. In this embodiment, the evaluation object is the photovoltaic power generation unit, and the comprehensive evaluation index is the power generation efficiency of the photovoltaic power generation unit.

[0090] In some embodiments, the curve characteristics of the power time series curve of the photovoltaic power generation unit can also be divided into benefit-type characteristics and cost-type characteristics. For example, the average curvature and the smaller the frequency of concavity and convexity change of the power time series curve of the photovoltaic power generation unit, the better the power generation efficiency of the photovoltaic power generation unit; the larger the integral area of the power time series curve of the photovoltaic power generation unit within the target duration, the larger the cumulative power of the photovoltaic power generation unit within the target duration, and the better the power generation efficiency of the photovoltaic power generation unit. Therefore, the benefit-type characteristics may include: the integral area of the power time series curve of the photovoltaic power generation unit within the target duration; the cost-type characteristics may include: the average curvature and / or the characterization information of the frequency of concavity and convexity change. Among them, the characterization information of the frequency of concavity and convexity change may be the number of folds of the power time series curve of the photovoltaic power generation unit, or the extreme value change frequency of the power time series curve of the photovoltaic power generation unit, etc.

[0091] Correspondingly, the computing device 20 can determine the benefit-type rank sum ratio of multiple photovoltaic power generation units according to the benefit-type characteristics of multiple power time series curves corresponding to the multiple photovoltaic power generation units 10. Specifically, the benefit-type rank sum ratio can be expressed as:

[0092]

[0093] Among them, in formula (8), n represents the total number of power time series curves, i represents the i-th power time series curve, corresponding to the i-th photovoltaic power generation unit 10. RSR i represents the benefit-type rank sum ratio of the i-th photovoltaic power generation unit corresponding to the i-th power time series curve. x i represents the benefit-type characteristic of the i-th power time series curve.

[0094] In this embodiment, in formula (8), x iIt represents the integral area of the i-th power time series curve within the target duration. Correspondingly, for any power time series curve P(t), the maximum and minimum values of the integral areas of multiple power time series curves corresponding to multiple photovoltaic power generation units 10 within the target duration can be determined according to the integral areas of the multiple power time series curves within the target duration; and the integral area of the power time series curve P(t) within the target duration, as well as the maximum and minimum values of the integral areas of the multiple power time series curves within the target duration, are substituted into the above formula (8) for calculation to obtain the benefit type rank sum ratio of the photovoltaic power generation unit corresponding to the power time series curve P(t).

[0095] The calculation device 20 can also determine the cost type rank sum ratio of multiple photovoltaic power generation units according to the cost type characteristics of multiple power time series curves corresponding to the multiple photovoltaic power generation units 10. Specifically, the cost type rank sum ratio can be expressed as:

[0096]

[0097] Among them, in formula (9), n represents the total number of power time series curves, i represents the i-th power time series curve, corresponding to the i-th photovoltaic power generation unit 10. RSR i represents the cost type rank sum ratio of the i-th photovoltaic power generation unit corresponding to the i-th power time series curve. y i represents the cost type characteristic of the i-th power time series curve.

[0098] In this embodiment, y i represents the characterization information of the average curvature or the change frequency of concavity and convexity of the i-th power time series curve (such as the number of folds or the change frequency of extreme values). Correspondingly, for the average curvature of any power time series curve P(t), the maximum and minimum values of the average curvatures of multiple power time series curves corresponding to multiple photovoltaic power generation units 10 can be determined according to the average curvatures of the multiple power time series curves; and the average curvature of the power time series curve P(t), as well as the maximum and minimum values of the average curvatures of the multiple power time series curves, are substituted into the above formula (9) for calculation to obtain the average curvature type cost type rank sum ratio of the photovoltaic power generation unit corresponding to the power time series curve P(t).

[0099] For the average curvature of any power time series curve P(t), the maximum and minimum values of the characterization information of the change frequency of concavity and convexity of multiple power time series curves can be determined according to the characterization information of the change frequency of concavity and convexity of multiple power time series curves corresponding to multiple photovoltaic power generation units 10; and the characterization information of the change frequency of concavity and convexity of the power time series curve P(t), as well as the maximum and minimum values of the characterization information of the change frequency of concavity and convexity of the multiple power time series curves, are substituted into the above formula (9) for calculation to obtain the concavity and convexity change frequency type cost type rank sum ratio of the photovoltaic power generation unit corresponding to the power time series curve P(t).

[0100] Further, the efficacy rank sum ratio of multiple photovoltaic power generation units 10 can be determined according to the benefit type rank sum ratio and cost type rank sum ratio of the multiple photovoltaic power generation units 10. Optionally, for any photovoltaic power generation unit 10, the mean value of the benefit type rank sum ratio and cost type rank sum ratio of the photovoltaic power generation unit 10 can be calculated as the efficacy rank sum ratio of the photovoltaic power generation unit 10.

[0101] For example, in some embodiments, the benefit type characteristics of the power time series curve include: the integral area of the power time series curve of the photovoltaic power generation unit over the target duration; the cost type characteristics may include: the average curvature of the power time series curve of the photovoltaic power generation unit and the characterization information of the concavity and convexity change frequency, then the mean values of the benefit type rank sum ratio, the average curvature type cost type rank sum ratio, and the concavity and convexity change frequency type cost type rank sum ratio of the photovoltaic power generation unit 10 can be calculated as the efficacy rank sum ratio of the photovoltaic power generation unit 10. That is:

[0102]

[0103] In Equation (10), RSR i represents the efficacy rank sum ratio of the i-th photovoltaic power generation unit corresponding to the i-th power time series curve; RSR1 i represents the benefit type rank sum ratio of the i-th photovoltaic power generation unit corresponding to the i-th power time series curve; RSR2 i represents the average curvature type cost type rank sum ratio of the i-th photovoltaic power generation unit corresponding to the i-th power time series curve; RSR3 i represents the concavity and convexity change frequency type cost type rank sum ratio of the i-th photovoltaic power generation unit corresponding to the i-th power time series curve.

[0104] Based on the efficacy rank sum ratio calculation method shown in the above embodiments, the efficacy rank sum ratios of multiple photovoltaic power generation units 10 can be obtained. Since the efficacy rank sum ratio can be used to comprehensively evaluate the power generation efficacy of the photovoltaic power generation unit, the computing device 20 can perform power generation efficacy detection on multiple photovoltaic power generation units 10 according to the efficacy rank sum ratios of multiple photovoltaic power generation units 10.

[0105] Specifically, the computing device 20 can perform Probit regression on the efficacy rank sum ratios of multiple photovoltaic power generation units to obtain the Probit values of multiple photovoltaic power generation units. The distribution of RSR refers to expressing a specific cumulative frequency with Probit values. The Probit value is obtained by matching the percentage (evaluation rank number / n * 100%) in the "Percentage and Probability Unit Conversion Table".

[0106] Specifically, the computing device 20 can sort the effectiveness rank sum ratios of multiple photovoltaic power generation units in ascending order; and determine the cumulative frequency of each effectiveness rank sum ratio according to the effectiveness rank sum ratio of the photovoltaic power generation unit, and use the cumulative frequency of each effectiveness rank sum ratio as the evaluation rank number R of the effectiveness rank sum ratio. Further, the cumulative frequency of each effectiveness rank sum ratio can be calculated according to the evaluation rank number R of each effectiveness rank sum ratio. Among them, for any effectiveness rank sum ratio except the one sorted at the end, its cumulative frequency is equal to (R / k * 100%). Where k represents the number of different values of the effectiveness rank sum ratios of multiple photovoltaic power generation units. The cumulative frequency of the effectiveness rank sum ratio sorted at the end can be corrected using (1 - 1 / 4n) × 100%.

[0107] Further, according to the cumulative frequency of each effectiveness rank sum ratio, the pre-set percentage and probit value comparison table can be queried to obtain the probit values corresponding to each effectiveness rank sum ratio. Among them, the pre-set percentage and probit value comparison table is the standard normal distribution function value table.

[0108] Further, the computing device 20 can use the probit values of multiple photovoltaic power generation units 10 as independent variables and the effectiveness rank sum ratios of multiple photovoltaic power generation units 10 as dependent variables to calculate the regression equation between the effectiveness rank sum ratio and the probit value. Specifically, assuming RSR = a * Probit + b, the probit values of multiple photovoltaic power generation units 10 can be used as independent variables and the effectiveness rank sum ratios of multiple photovoltaic power generation units 10 can be used as dependent variables, and substituted into the above equation RSR = a * Probit + b to calculate the values of a and b, and then obtain the regression equation between the effectiveness rank sum ratio and the probit value.

[0109] Further, the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units can be determined according to the regression equation between the effectiveness rank sum ratio and the probit value. Among them, according to the regression equation between the effectiveness rank sum ratio and the probit value, to determine the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units, the effectiveness rank sum ratio of multiple photovoltaic power generation units can be mapped to the normal distribution function, which is convenient for subsequent grading of the power generation effectiveness of multiple photovoltaic power generation units.

[0110] Further, the power generation effectiveness of multiple photovoltaic power generation units 10 can be graded according to the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units 10 to obtain the high and low conditions of the power generation effectiveness of multiple photovoltaic power generation units 10, so as to realize the detection of the power generation effectiveness of multiple photovoltaic power generation units 10. For example, according to the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units 10, the power generation effectiveness of multiple photovoltaic power generation units can be divided into three grades: high, medium, and low, etc.

[0111] Further, the computing device 20 may also send a prompt message to the monitoring device of the target photovoltaic power generation unit whose power generation efficiency is classified as low according to the power generation efficiency levels of multiple photovoltaic power generation units 10. Such as "The power generation efficiency of photovoltaic power generation unit XXX is low, please check", etc. Among them, "XXX" in the photovoltaic power generation unit XXX represents the identifier of the target photovoltaic power generation unit, and the user can determine which the target photovoltaic power generation unit is based on this identifier, etc. This prompt message can enable the maintenance personnel of the target photovoltaic power generation unit to perform maintenance on the target photovoltaic power generation unit, etc.

[0112] In addition to the above system embodiments, the embodiments of the present application also provide a power generation efficiency detection method. The power generation efficiency detection method provided by the embodiments of the present application will be exemplarily described below.

[0113] Figure 8 It is a schematic flowchart of the power generation efficiency detection method provided by the embodiments of the present application. As Figure 8 shown, the power generation efficiency detection method mainly includes:

[0114] 801. Obtain multiple power time series curves of multiple photovoltaic power generation units; each photovoltaic power generation unit corresponds to at least one power time series curve.

[0115] 802. Extract curve features from multiple power time series curves to obtain the curve features of multiple power time series curves.

[0116] 803. Detect the power generation efficiency of multiple photovoltaic power generation units according to the curve features of multiple power time series curves.

[0117] Regarding the working principle and implementation manner of the photovoltaic power generation unit, reference can be made to the relevant content of the above system embodiments, which will not be elaborated here. In this embodiment, according to the analysis of the power time series curve of the photovoltaic power generation unit in the normal power generation state and the power time series curve of the photovoltaic power generation unit with low power generation efficiency in the foregoing embodiments, it can be seen that the power time series curves of the photovoltaic power generation unit with normal power generation efficiency and the photovoltaic power generation unit with low power generation efficiency are completely different. Therefore, to a certain extent, the power time series curve of the photovoltaic power generation unit can reflect the level of the power generation efficiency of the photovoltaic power generation unit.

[0118] Based on this, in order to detect the level of the power generation efficiency of the photovoltaic power generation unit, in step 801, multiple power time series curves of multiple photovoltaic power generation units can be obtained. Among them, the multiple photovoltaic power generation units are the photovoltaic power generation units to be detected for their power generation efficiency. Each photovoltaic power generation unit corresponds to at least one power time series curve. Optionally, each photovoltaic power generation unit may correspond to one power time series curve.

[0119] In some embodiments, a power collection device may be used to collect the power time-series data of each photovoltaic power generation unit within a sampling period, and each power data corresponds to a time point within the sampling period. In the embodiments of the present application, the specific value of the sampling period is not limited. Optionally, the sampling period may be 1 day or multiple days. Multiple days means 2 days or more. Generally, the sampling period may be 1 day. Further, based on the power time-series data of the photovoltaic power generation unit within the sampling period, the power time-series curve of the photovoltaic power generation unit may be determined.

[0120] Further, in step 802, curve feature extraction may be performed on the power time-series curve to obtain the curve features of each power time-series curve. The curve features of the power time-series curve are features related to the shape of the power time-series curve, and to a certain extent, these curve features can reflect the power generation efficiency of the photovoltaic power generation unit corresponding to the power time-series curve.

[0121] Combined with the foregoing Figure 3 and Figure 4 the power time-series curves shown in different power generation efficiency states, it can be seen that for a photovoltaic power generation unit with sufficient light and good condition, its power generation efficiency is relatively high, the corresponding power time-series curve is relatively smooth, and the average curvature of the power time-series curve is relatively small. While a photovoltaic power generation unit that is frequently disturbed by external environmental factors and / or has internal abnormalities has a relatively low power generation efficiency, the corresponding power time-series curve is complex and changeable, and the average curvature is relatively large. Based on this, the curve features of the power time-series curve may include: the average curvature of the power time-series curve. Correspondingly, the radius of the osculating circle of each power sampling point on the power time-series curve P(t) can be calculated.

[0122] In practical applications, the collected power time-series data is discrete sampling data, then the first-order difference of the power time-series curve can be used to represent the first-order derivative of the power time-series curve, and the second-order difference can be used to represent the second-order derivative of the power time-series curve. Correspondingly, based on the power and time corresponding to each power sampling point on the power time-series curve P(t), the first-order difference and the second-order difference of the power sampling points on the power time-series curve P(t) can be calculated; and based on the first-order difference and the second-order difference of the power sampling points on the power time-series curve P(t), the radius of the osculating circle of the power sampling points on the power time-series curve P(t) can be calculated. Further, the reciprocal of the radius of the osculating circle of the power sampling points on the power time-series curve P(t) can be used as the curvature of the power sampling points on the power time-series curve P(t).

[0123] Further, based on the curvature of each power sampling point on the power time-series curve P(t), the average curvature of this power time-series curve can be calculated as the curve feature of the power time-series curve P(t). Specifically, the mean value of the curvature of each power sampling point on the power time-series curve P(t) can be calculated as the average curvature of the power time-series curve P(t).

[0124] In some other embodiments, the curve features of the power time sequence curve may include: the change frequency of the concavity and convexity of the power time sequence curve. Accordingly, the characterization information of the change frequency of the concavity and convexity of the power time sequence curve P(t) can be extracted from the power time sequence curve P(t) as the curve feature of the power time sequence curve P(t). Among them, the change frequency of the concavity and convexity of the power time sequence curve of a photovoltaic power generation unit with sufficient light and good condition is low; for a photovoltaic power generation unit frequently disturbed by external environmental factors and / or having abnormalities inside, the change frequency of the concavity and convexity of its power time sequence curve is high.

[0125] Among them, the characterization information of the change frequency of the concavity and convexity of the power time sequence curve P(t) refers to the information that can be used to reflect the change frequency of the concavity and convexity of the power time sequence curve P(t).

[0126] In some embodiments, since the extreme value of the curve can be used to determine the concavity and convexity of the curve, and the change frequency of the extreme value of the curve can reflect the change frequency of the concavity and convexity of the curve, therefore, the change frequency of the extreme value of the power time sequence curve P(t) can be used as the characterization information of the change frequency of the concavity and convexity of the power time sequence curve P(t).

[0127] Accordingly, the extreme values of the power time sequence curve P(t) can be calculated, and based on the time interval between any two adjacent extreme values, the average time interval between the extreme values of the power time sequence curve P(t) can be calculated; then, the reciprocal of the average time interval between the extreme values of the power time sequence curve P(t) can be used as the change frequency of the extreme value of the power time sequence curve P(t). Among them, the change frequency of the extreme value of the power time sequence curve P(t) is the characterization information of the change frequency of the concavity and convexity of the power time sequence curve P(t).

[0128] In some other embodiments, since the extreme value of the curve can be used to determine the concavity and convexity of the curve, the change frequency of the extreme value of the curve can reflect the change frequency of the concavity and convexity of the curve, and the number of extreme values of the curve determines the number of folds of the curve. In this embodiment, the curve segment between one extreme value and the next extreme value of the curve is one fold. Among them, the curve with a higher change frequency of concavity and convexity has more folds; the curve with a lower change frequency of concavity and convexity has fewer folds. The fewer the number of folds of the curve, the smoother the curve and the lower the change frequency of concavity and convexity. Based on this, the number of folds (Folds) of the power time sequence curve P(t) can be used to represent the characterization information of the change frequency of the concavity and convexity of the power time sequence curve P(t).

[0129] Accordingly, the extreme values of the power time sequence curve P(t) can be calculated, and based on the number of extreme values of the power time sequence curve P(t) calculated, the number of folds of the power time sequence curve P(t) can be determined as the characterization information of the change frequency of the concavity and convexity of the power time sequence curve P(t). Among them, the curve segment between two adjacent extreme values is one fold of the power time sequence curve P(t).

[0130] In some other embodiments, in combination with Figure 3 and Figure 4 From the power timing curves shown, it can be seen that for a photovoltaic power generation unit with sufficient light and good condition, its power generation efficiency is relatively high, and the integral area of the power timing curve over the corresponding target duration is relatively large; while a photovoltaic power generation unit that is frequently interfered by external environmental factors and / or has internal abnormalities has a relatively low power generation efficiency, and the integral area of the corresponding power timing curve over the corresponding duration is relatively small.

[0131] Since the physical meaning of the power timing curve is the power generation power of the photovoltaic power generation unit at each moment, therefore, the integral area of the power timing curve P(t) over the corresponding target duration can represent the cumulative power of the photovoltaic power generation unit over the target duration. To a certain extent, the integral area of the power timing curve of the photovoltaic power generation unit over the target duration can reflect the power generation efficiency of the photovoltaic power generation unit. Based on this, the curve characteristics of the power timing curve can include: the integral area of the power timing curve over the target duration.

[0132] Correspondingly, the integral area of the power timing curve P(t) over the target duration can be calculated as the curve characteristic of the power timing curve P(t). Wherein, the target duration is the sampling duration of the power timing curve P(t); the start and end times of the target duration are the start and end times of the sampling of the power timing curve P(t).

[0133] The curve characteristics of the power timing curve P(t) shown in the above embodiments are only for illustrative purposes and do not constitute a limitation. In the embodiments of the present application, the curve characteristics of the power timing curve P(t) can include at least one of: the average curvature of the power timing curve P(t), the characterization information of the frequency of concavity and convexity change of the power timing curve P(t), and the integral area of the power timing curve P(t) over the target duration. Preferably, the curve characteristics of the power timing curve P(t) can include multiple of the average curvature of the power timing curve P(t), the characterization information of the frequency of concavity and convexity change of the power timing curve P(t), and the integral area of the power timing curve P(t) over the target duration. Multiple means 2 or more than 2. For example, the curve characteristics of the power timing curve P(t) can include: the average curvature of the power timing curve P(t), the characterization information of the frequency of concavity and convexity change of the power timing curve P(t), and the integral area of the power timing curve P(t) over the target duration, etc.

[0134] Since the curve characteristics of the power timing curve P(t) of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit, based on this, in step 803, the power generation efficiency of multiple photovoltaic power generation units can be detected according to the curve characteristics of multiple power timing curves corresponding to the multiple photovoltaic power generation units. It should be noted that in the embodiments of the present application, the detection of the power generation efficiency of the photovoltaic power generation unit is mainly to evaluate the quality of the power generation efficiency of the photovoltaic power generation unit, and it evaluates the high or low or good or bad of the power generation efficiency of the photovoltaic power generation unit.

[0135] In this embodiment, the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency characteristics of the photovoltaic power generation unit. By extracting the curve characteristics of the power time series curve of the photovoltaic power generation unit, the curve characteristics of the power time series curve of the photovoltaic power generation unit are obtained, realizing the quantification of the geometric shape of the power time series curve of the photovoltaic power generation unit; and according to the power time series curves corresponding to multiple photovoltaic power generation units, the power generation efficiency of multiple photovoltaic power generation units is evaluated, realizing the automatic detection of the power generation efficiency of the photovoltaic power generation unit, without the need for manual inspection of the photovoltaic power generation unit, which can reduce the detection time of the power generation efficiency of the photovoltaic power generation unit and improve the power generation efficiency detection speed.

[0136] On the other hand, the manual inspection method is used to check the power generation efficiency of the photovoltaic power generation unit. The inspection workload is large, and it is easy to cause missed inspections or even misinspections. The embodiment of the present application uses the characteristic that the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit to realize the automatic detection of the power generation efficiency of the photovoltaic power generation unit. Compared with the manual inspection method, the missed inspection probability of the photovoltaic power generation unit can also be reduced. Since the automatic detection reduces the error of human factors, the accuracy of the power generation efficiency detection can also be improved.

[0137] In addition, the embodiment of the present application uses the characteristic that the curve characteristics of the power time series curve of the photovoltaic power generation unit can reflect the power generation efficiency of the photovoltaic power generation unit to realize the automatic detection of the power generation efficiency of the photovoltaic power generation unit. The requirements for data collection are simple, without requiring a large amount of historical time series data, nor marking the quality of the power generation efficiency of the historical time series data, nor requiring meteorological data, which can reduce the data collection cost.

[0138] In some embodiments of the present application, when detecting the power generation efficiency of multiple photovoltaic power generation units according to the curve characteristics of multiple power time series curves corresponding to multiple photovoltaic power generation units, the efficacy rank sum ratio (RSR) of multiple photovoltaic power generation units can be determined according to the curve characteristics of multiple power time series curves corresponding to multiple photovoltaic power generation units.

[0139] In some embodiments, the curve characteristics of the power time series curve of the photovoltaic power generation unit can also be divided into benefit type characteristics and cost type characteristics. For example, the average curvature of the power time series curve of the photovoltaic power generation unit and the smaller the change frequency of concavity and convexity, the better the power generation efficiency of the photovoltaic power generation unit; the larger the integral area of the power time series curve of the photovoltaic power generation unit in the target time period, the larger the cumulative power of the photovoltaic power generation unit in the target time period, and the better the power generation efficiency of the photovoltaic power generation unit. Therefore, the benefit type characteristics can include: the integral area of the power time series curve of the photovoltaic power generation unit in the target time period; the cost type characteristics can include: the average curvature of the power time series curve of the photovoltaic power generation unit and / or the characterization information of the concavity / convexity change frequency. Among them, the characterization information of the concavity / convexity change frequency can be the number of folds of the power time series curve of the photovoltaic power generation unit, or the extreme value change frequency of the power time series curve of the photovoltaic power generation unit, etc.

[0140] Correspondingly, the benefit type rank sum ratio of multiple photovoltaic power generation units can be determined according to the benefit type characteristics of multiple power time series curves corresponding to multiple photovoltaic power generation units. For the specific calculation method of the benefit type rank sum ratio, reference can be made to the relevant content of the foregoing system embodiment, which will not be elaborated here.

[0141] In this embodiment, the benefit type characteristics include the integral area of the power time series curve within the target time period. Correspondingly, for any power time series curve P(t), the maximum and minimum values of the integral areas of multiple power time series curves corresponding to multiple photovoltaic power generation units within the target time period can be determined according to the integral areas of multiple power time series curves within the target time period; and the integral area of the power time series curve P(t) within the target time period, and the maximum and minimum values of the integral areas of multiple power time series curves within the target time period are substituted into the above formula (8) for calculation to obtain the benefit type rank sum ratio of the photovoltaic power generation unit corresponding to the power time series curve P(t).

[0142] Furthermore, the cost type rank sum ratio of multiple photovoltaic power generation units can be determined according to the cost type characteristics of multiple power time series curves corresponding to multiple photovoltaic power generation units. For the specific calculation method of the cost type rank sum ratio, reference can be made to the relevant content of the foregoing embodiment, which will not be elaborated here.

[0143] In this embodiment, the cost type characteristics include: the average curvature of the i-th power time series curve, and / or the characterization information of the concavity / convexity change frequency (such as the number of folds or the extreme value change frequency). Correspondingly, for the average curvature of any power time series curve P(t), the maximum and minimum values of the average curvatures of multiple power time series curves corresponding to multiple photovoltaic power generation units can be determined according to the average curvatures of multiple power time series curves; and the average curvature of the power time series curve P(t), and the maximum and minimum values of the average curvatures of multiple power time series curves are substituted into the foregoing formula (9) for calculation to obtain the average curvature type cost type rank sum ratio of the photovoltaic power generation unit corresponding to the power time series curve P(t).

[0144] For the average curvature of any power time series curve P(t), the maximum and minimum values of the characterization information of the concavity and convexity change frequencies of multiple power time series curves corresponding to multiple photovoltaic power generation units 10 can be determined according to the characterization information of the concavity and convexity change frequencies of the multiple power time series curves; and the characterization information of the concavity and convexity change frequency of the power time series curve P(t), as well as the maximum and minimum values of the characterization information of the concavity and convexity change frequencies of the multiple power time series curves, are substituted into the foregoing formula (9) for calculation to obtain the concavity and convexity change frequency type cost rank sum ratio of the photovoltaic power generation unit corresponding to the power time series curve P(t).

[0145] Furthermore, the efficiency rank sum ratio of multiple photovoltaic power generation units can be determined according to the benefit type rank sum ratio and the cost type rank sum ratio of the multiple photovoltaic power generation units. Optionally, for any photovoltaic power generation unit, the average value of the benefit type rank sum ratio and the cost type rank sum ratio of the photovoltaic power generation unit can be calculated as the efficiency rank sum ratio of the photovoltaic power generation unit.

[0146] For example, in some embodiments, the benefit type features of the power time series curve include: the integral area of the power time series curve of the photovoltaic power generation unit over the target duration; the cost type features may include: the average curvature of the power time series curve of the photovoltaic power generation unit and the characterization information of the concavity and convexity change frequency, then the average value of the benefit type rank sum ratio, the average curvature type cost rank sum ratio, and the concavity and convexity change frequency type cost rank sum ratio of the photovoltaic power generation unit can be calculated as the efficiency rank sum ratio of the photovoltaic power generation unit.

[0147] Based on the efficiency rank sum ratio calculation method shown in the above embodiments, the efficiency rank sum ratios of multiple photovoltaic power generation units can be obtained. Since the efficiency rank sum ratio can be used to comprehensively evaluate the power generation efficiency of photovoltaic power generation units, therefore, the power generation efficiency of multiple photovoltaic power generation units can be detected according to the efficiency rank sum ratios of the multiple photovoltaic power generation units.

[0148] Specifically, a probit regression can be performed on the efficiency rank sum ratios of multiple photovoltaic power generation units to obtain the probit values of the multiple photovoltaic power generation units. For the specific implementation of performing a probit regression on the efficiency rank sum ratios of multiple photovoltaic power generation units, reference can be made to the relevant content of the foregoing system embodiments, which will not be elaborated here.

[0149] Furthermore, taking the probit values of multiple photovoltaic power generation units as independent variables and the efficiency rank sum ratios of multiple photovoltaic power generation units as dependent variables, a regression equation between the efficiency rank sum ratio and the probit value is calculated.

[0150] Further, the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units can be determined according to the regression equation between the effectiveness rank sum ratio and the probit value. Among them, determining the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units according to the regression equation between the effectiveness rank sum ratio and the probit value can map the effectiveness rank sum ratio of multiple photovoltaic power generation units onto the normal distribution function, which is convenient for subsequent grading of the power generation effectiveness of multiple photovoltaic power generation units.

[0151] Further, the power generation effectiveness of multiple photovoltaic power generation units can be graded according to the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units, so as to obtain the high and low conditions of the power generation effectiveness of multiple photovoltaic power generation units, and realize the detection of the power generation effectiveness of multiple photovoltaic power generation units. For example, the power generation effectiveness of multiple photovoltaic power generation units can be divided into three grades: high, medium, and low according to the estimated value of the effectiveness rank sum ratio of multiple photovoltaic power generation units.

[0152] Further, a prompt message can also be sent to the monitoring device of the target photovoltaic power generation unit whose power generation effectiveness is graded as low according to the high and low conditions of the power generation effectiveness of multiple photovoltaic power generation units. Such as "The power generation effectiveness of photovoltaic power generation unit XXX is low, please check", etc. Among them, "XXX" in the photovoltaic power generation unit XXX represents the identifier of the target photovoltaic power generation unit, and the user can determine which target photovoltaic power generation unit it is according to this identifier. This prompt message can enable the maintenance personnel of the target photovoltaic power generation unit to perform maintenance on the target photovoltaic power generation unit.

[0153] Similarly, the power generation effectiveness detection method provided by the embodiments of the present application can be deployed on any computing device. Optionally, the rendering method provided by the embodiments of the present application can also be deployed on a cloud server as a software as a service (SaaS) application. For the cloud server deployed with this SaaS application, in response to a request to invoke a target service, the steps in the above power generation effectiveness detection method can be executed. The specific implementation is as Figure 9 shown, this method is applicable to a cloud server and mainly includes:

[0154] 901. In response to a request to invoke a target service, determine the processing resources corresponding to the target service.

[0155] 902. Use the processing resources corresponding to the target service to obtain multiple power time series curves of multiple photovoltaic power generation units; each photovoltaic power generation unit corresponds to at least one power time series curve.

[0156] 903. Use the processing resources corresponding to the target service to extract the curve features of multiple power time series curves to obtain the curve features of multiple power time series curves.

[0157] 904. Detect the power generation efficiency of multiple photovoltaic power generation units by using the processing resources corresponding to the target service according to the curve characteristics of multiple power time series curves.

[0158] In this embodiment, the target service refers to the service that provides the power generation efficiency detection method. The processing resources corresponding to the target service refer to the processing resources required to execute the above-mentioned power generation efficiency detection method, including but not limited to: processor resources, memory resources, and input / output (I / O) resources, etc.

[0159] The power generation efficiency method provided in this embodiment can be deployed on a cloud server to provide the power generation efficiency service of the target application, that is, the target service, to users. The user can be the user or customer of the target service, etc. Optionally, the cloud server can provide an application programming interface (API) to the using party. The service requestor (i.e., the user) can call the API to call the target service. Correspondingly, the request for calling the target service is implemented as a call event generated by calling the API. The service requestor (i.e., the user) can also call the target service through remote procedure call (RPC) or remote direct memory access (RDMA) technology.

[0160] For the cloud server, in response to the request for calling the target service, it can determine the processing resources corresponding to the target service; and use the processing resources corresponding to the target service to execute the steps of step 902 - step 904 to implement the detection of the power generation efficiency of multiple photovoltaic power generation units. For the specific implementation manners of step 902 - step 904, reference can be made to the relevant content above Figure 8 and will not be elaborated here.

[0161] It should be noted that the execution subject of each step of the method provided in the above embodiment can be the same device, or the method can also be executed by different devices as the execution subject. For example, the execution subjects of step 801 and 802 can be device A; for another example, the execution subject of step 801 can be device A, and the execution subject of step 802 can be device B; and so on.

[0162] In addition, in some processes described in the above embodiments and the accompanying drawings, there are multiple operations that appear in a specific order, but it should be clearly understood that these operations can be executed not in the order in which they appear in this article or in parallel. The operation numbers such as 801, 802, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and these operations can be executed in sequence or in parallel.

[0163] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing computer instructions, which, when executed by one or more processors, cause the one or more processors to execute the steps in the above power generation efficiency method.

[0164] To verify the effectiveness of the power generation efficiency detection method provided by the embodiment of the present application, the inventor of the present application uses the power time series dataset of open photovoltaic sites to verify the effectiveness of the power generation efficiency detection method provided by the embodiment of the present application. Among them, the power time series dataset of the open photovoltaic sites includes: the power time series data of 137 photovoltaic sites. The power time series data is sampled every five minutes. Figure 10 Only the power time series curves of some photovoltaic sites on a certain day are shown in the figure as an example. During the verification process, a photovoltaic site is used as a photovoltaic power generation unit. Figure 10 In the figure, Power_0 to Power_12 respectively represent the power time series curves of 13 photovoltaic sites such as photovoltaic site 0-12 on a certain day. Figure 10 It can be seen that the photovoltaic site starts to work after sunrise at 6 am and stops working after sunset at 6 pm. Figure 10 The power time series (P-T) curves of some sites of the photovoltaic sites shown are close to a horseshoe shape and are relatively plump, while the power time series curves of some other photovoltaic sites are complex and changeable, very tortuous, and the power generation efficiency is low.

[0165] Using the power generation efficiency detection method provided by the embodiment of the present application, curve features such as the average curvature, the number of folds, and the integral area of the power time series curves of 137 photovoltaic sites on that day are extracted; and according to the curve features such as the average curvature, the number of folds, and the integral area of the power time series curves of 137 photovoltaic sites, the efficiency rank sum ratio (RSR) of each photovoltaic site is determined by using the method provided in the foregoing embodiment, and the curve features of the power time series curves of the photovoltaic sites and the RSR values of 137 photovoltaic sites are obtained as shown in Table 1 below.

[0166] Table 1 Curve features of the power time series curves of photovoltaic sites and RSR of 137 photovoltaic sites

[0167] Photovoltaic site Average curvature Number of folds Integral area RSR 0 0.409952 0.480769 999.1 0.300246 1 0.089453 0.301282 1948.1 0.716669 2 0.114178 0.346154 1465.3 0.633407 3 0.433157 0.544872 1255.3 0.239595 4 0.271786 0.410256 4429.3 0.635724 … … … … … 132 0.254736 0.391026 2854.8 0.579612 133 0.466189 0.532051 1380.4 0.238054 134 0.107983 0.378205 1074.5 0.586124 135 0.215030 0.435897 1820.6 0.506303 136 0.162800 0.378205 1216.1 0.560051

[0168] Furthermore, probit regression is performed on the RSR values of 137 photovoltaic sites, and the regression equation is verified to obtain Table 2 below.

[0169] Table 2 Coefficient verification results of the regression equation obtained by probit regression

[0170]

[0171] In Table 2 above, R-Squared (the square of the correlation coefficient R) is a value that measures the degree of correlation between variables. In multiple regression analysis, Adj.R-Square is the R-Squared of the sample adjusted according to the sample size and degrees of freedom. When validating a regression model, R-Squared is also known as the goodness of fit or coefficient of determination, and is used to represent the percentage of the variation in the dependent variable that can be explained by the fitted model. The closer R-Squared is to 1, the better the fitting effect of the regression model.

[0172] The main function of the linear regression analysis of variance table is to judge the regression effect of the regression model through the F-test, that is, to test whether the linear relationship between the dependent variable and all independent variables is significant, and whether it is appropriate to describe their relationship with a linear model. There are mainly five indicators: sum of squares, degrees of freedom (Df), mean square (MS), F (F statistic), and significance (P value).

[0173] In Table 2 above, Prob(F-statistic) is the probability of the F statistic, which is used to test the overall significance of the equation. AIC is called the Akaike information criterion, and BIC is called the Bayesian information measure. Both are criteria for evaluating the complexity of a statistical model and measuring the goodness of fit of a statistical model. The smaller the value, the better the corresponding model. The constant b represents the intercept b in the regression equation RSR = a*Probit + b in the foregoing embodiment, and a represents the slope a of the regression equation. In Table 2, a = 0.1281; b = -01299.

[0174] The Durbin-Watson (D.W) test statistic is used to test whether the residuals of the regression model are autocorrelated. The Omnibus test is a method for testing the overall goodness of fit of a model. It is based on the joint significance of all coefficients in the model to determine whether the model is suitable for predicting or explaining data. Prob(Omnibus) is the test probability of data normality based on kurtosis and skewness.

[0175] Among them, skewness is a measure of the direction and degree of skewness of the statistical data distribution. It is a numerical characteristic of the asymmetry of the statistical data distribution, and is a characteristic number that characterizes the degree of asymmetry of the probability distribution density curve relative to the mean. Kurtosis, also known as the kurtosis coefficient, is a characteristic number that characterizes the peak height of the probability density distribution curve at the mean. The kurtosis of a sample is a statistic compared with the normal distribution. If the kurtosis is greater than three, the shape of the peak is relatively sharp and steeper than the normal distribution peak.

[0176] The results of the Jarque-Bera (JB) test are mainly used to judge whether the data conforms to the overall normal distribution. Prob(JB) represents the significance (P value) of JB.

[0177] The condition number (Cond.No.) is used to measure whether there is multicollinearity among the independent variables of a multiple regression model. The value of the condition number is a positive number. The smaller this value is, the more it indicates that there is no multicollinearity problem among the independent variables.

[0178] In this application, the focus is mainly on the significance (P-value) of the coefficients of the regression equation. The significance (P-value) can be directly compared with the significance level [0.025, 0.975] to obtain the result. The significance (P-value) is the critical value of F at the significance level, and this is used to measure whether the test result is significant. If the significance (P-value) > 0.975, the result does not have significant statistical significance; if 0.025 < significance (P-value) < 0.975, the result has significant statistical significance; if the significance (P-value) < 0.0025, the result has extremely significant statistical significance. As shown in Table 2, the significance (P) value of the verification result of the regression equation in this application is 0.000, which is less than 0.025, and the regression coefficient is significant, indicating that the regression result is reliable.

[0179] Based on the obtained regression equation between the efficiency rank sum ratio and Probit: RSR = 0.1281 * Probit - 01299, the estimated values of the efficiency rank sum ratio of 137 photovoltaic sites can be calculated; and based on the estimated values of the efficiency rank sum ratio of 137 photovoltaic sites, the power generation efficiencies of 137 photovoltaic sites are classified into high and low grades, obtaining Figure 11 a batch of photovoltaic sites with high power generation efficiency as shown, and Figure 12 a batch of photovoltaic sites with low power generation efficiency as shown.

[0180] According to Figure 11 and Figure 12 the power generation efficiency classification results of the photovoltaic sites shown, it can be obtained that the power generation efficiency detection method provided by the embodiments of this application can accurately distinguish between photovoltaic sites with good power generation efficiency and those with poor power generation efficiency, that is, it can accurately detect the high and low power generation efficiencies of photovoltaic sites.

[0181] Figure 13 It is a schematic structural diagram of the electronic device provided by the embodiments of this application. As Figure 13 shown, the electronic device includes: a memory 13a and a processor 13b. Among them, the memory 13a is used to store computer programs. The processor 13b is coupled to the memory 13a and is used to execute the computer program to execute the steps in the power generation efficiency detection method provided by the foregoing embodiments. For the specific implementation manners of each step, reference can be made to the relevant descriptions of the foregoing embodiments, which will not be elaborated here.

[0182] In some alternative embodiments, as Figure 13As shown, the electronic device may further include optional components such as a communication component 13c, a power supply component 13d, a display component 13e, and an audio component 13f. Figure 13 Only some components are schematically shown, which does not mean that the electronic device must include Figure 13 all the components shown, nor does it mean that the electronic device can only include Figure 13 the components shown.

[0183] In addition, Figure 13 the components within the dashed box are optional components, rather than mandatory components, and can be determined according to the product form of the electronic device. The electronic device in this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a mobile phone, or an Internet of Things device; it can also be various server devices such as a traditional server, a cloud server, or a server cluster.

[0184] In the embodiment of the present application, the memory is used to store computer programs and can be configured to store various other data to support operations on the device where it is located. Among them, the processor can execute the computer programs stored in the memory to implement corresponding control logics. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disc.

[0185] In the embodiments of the present application, the processor may be any hardware processing device capable of executing the above method logic. Optionally, the processor may be a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or a Microcontroller Unit (MCU); it may also be a programmable device such as a Field-Programmable Gate Array (FPGA), a Programmable Array Logic (PAL), a General Array Logic (GAL), or a Complex Programmable Logic Device (CPLD); or an Advanced RISC Machines (ARM) or a System on Chip (SoC), etc., but not limited thereto.

[0186] In the embodiments of the present application, the communication component is configured to facilitate communication between the device where it is located and other devices in a wired or wireless manner. The device where the communication component is located may access a wireless network based on a communication standard, such as Wireless Fidelity (WiFi), 2G or 3G, 4G, 5G, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component may also be implemented based on Near Field Communication (NFC) technology, Radio Frequency Identification (RFID) technology, Infrared Data Association (IrDA) technology, Ultra Wide Band (UWB) technology, Bluetooth (BT) technology, or other technologies.

[0187] In the embodiments of the present application, the display component may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the display component includes a touch panel, the display component can be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors can sense not only the boundaries of touch or swipe actions but also detect the duration and pressure associated with the touch or swipe operations.

[0188] In the embodiments of the present application, the power supply component is configured to provide power to various components of the device where it is located. The power supply component may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device where the power supply component is located.

[0189] In the embodiments of the present application, the audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC). When the device where the audio component is located is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive external audio signals. The received audio signals can be further stored in the memory or sent via the communication component. In some embodiments, the audio component further includes a speaker for outputting audio signals. For example, for a device with a language interaction function, voice interaction with the user can be implemented through the audio component.

[0190] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0191] It also should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0192] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, read-only compact disc (CD-ROM), optical storage, etc.) that contain computer-usable program code.

[0193] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or a combination of multiple blocks.

[0194] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or a combination of multiple blocks.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, so that the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or a combination of multiple blocks.

[0196] In a typical configuration, a computing device includes one or more processors (such as CPUs), an input / output interface, a network interface, and a memory.

[0197] Memory may include non-permanent memory in the form of computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0198] The storage medium of a computer is a readable storage medium, also known as a readable medium. Readable storage media include permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of the storage medium of a computer include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassette tapes, disk storage, or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media do not include transitory media, such as modulated data signals and carrier waves.

[0199] It should also be noted that the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the above elements.

[0200] The above content is only an embodiment of the present application and is not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for detecting power generation efficiency, characterized in that, it includes: Obtaining multiple power time - series curves of multiple photovoltaic power generation units; each photovoltaic power generation unit corresponds to at least one power time - series curve; Performing curve feature extraction on the multiple power time - series curves to obtain the curve features of the multiple power time - series curves; Performing power generation efficiency detection on the multiple photovoltaic power generation units according to the curve features of the multiple power time - series curves.

2. The method according to claim 1, characterized in that, The performing curve feature extraction on the multiple power time - series curves to obtain the curve features of the multiple power time - series curves includes: For any one of the multiple power time - series curves, extracting the curvature of the power sampling points on the any one power time - series curve; calculating the average curvature of the any one power time - series curve according to the curvature of the power sampling points on the any one power time - series curve, and taking it as the curve feature of the any one power time - series curve; and / or, Extracting the characterization information of the concavity - convexity change frequency of the any one power time - series curve from the any one power time - series curve, and taking it as the curve feature of the any one power time - series curve; and / or, Calculating the integral area of the any one power time - series curve within a target time period according to the any one power time - series curve, and taking it as the curve feature of the any one power time - series curve; wherein, the start and end times corresponding to the target time period are the sampling start and end times corresponding to the any one power time - series curve.

3. The method according to claim 2, characterized in that, The extracting the curvature of the power sampling points on the any one power time - series curve includes: Calculating the radius of the osculating circle of the power sampling points on the any one power time - series curve; Taking the reciprocal of the radius of the osculating circle of the power sampling points on the any one power time - series curve as the curvature of the power sampling points on the any one power time - series curve.

4. The method according to claim 3, characterized in that, The calculating the radius of the osculating circle of the power sampling points on the any one power time - series curve includes: Calculating the first - order difference and the second - order difference of the power sampling points on the any one power time - series curve according to the power and time corresponding to the power sampling points on the any one power time - series curve; Calculating the radius of the osculating circle of the power sampling points on the any one power time - series curve according to the first - order difference and the second - order difference of the power sampling points on the any one power time - series curve.

5. The method according to claim 2, characterized in that, The extracting the characterization information of the concavity - convexity change frequency of the any one power time - series curve from the any one power time - series curve includes: Calculating the extreme values of the any one power time - series curve; Determining the number of folds of the any one power time - series curve according to the number of extreme values of the any one power time - series curve, and taking it as the characterization information of the concavity - convexity change frequency of the any one power time - series curve; wherein, the curve segment between two adjacent extreme values is one fold of the any one power time - series curve.

6. The method according to claim 1, characterized in that, The performing power generation efficiency detection on the multiple photovoltaic power generation units according to the curve features of the multiple power time - series curves includes: Determine the efficiency rank sum ratio of the multiple photovoltaic power generation units according to the curve characteristics of the multiple power time series curves; Perform power generation efficiency detection on the multiple photovoltaic power generation units according to the efficiency rank sum ratio of the multiple photovoltaic power generation units.

7. The method according to claim 6, characterized in that the curve characteristics of the power time series curve include: benefit type characteristics and cost type characteristics; the determining the efficiency rank sum ratio of the multiple photovoltaic power generation units according to the curve characteristics of the multiple power time series curves includes: Determine the benefit type rank sum ratio of the multiple photovoltaic power generation units according to the benefit type characteristics of the multiple power generation time series curves; Determine the cost type rank sum ratio of the multiple photovoltaic power generation units according to the cost type characteristics of the multiple power time series curves; Determine the efficiency rank sum ratio of the multiple photovoltaic power generation units according to the benefit type rank sum ratio and the cost type rank sum ratio of the multiple photovoltaic power generation units.

8. The method according to claim 7, characterized in that the determining the efficiency rank sum ratio of the multiple photovoltaic power generation units according to the benefit type rank sum ratio and the cost type rank sum ratio of the multiple photovoltaic power generation units includes: For any photovoltaic power generation unit, calculate the mean value of the benefit type rank sum ratio and the cost type rank sum ratio of the any photovoltaic power generation unit as the efficiency rank sum ratio of the any photovoltaic power generation unit.

9. The method according to claim 6, characterized in that the performing power generation efficiency detection on the multiple photovoltaic power generation units according to the efficiency rank sum ratio of the multiple photovoltaic power generation units includes: Perform probit regression on the efficiency rank sum ratio of the multiple photovoltaic power generation units to obtain the probit values of the multiple photovoltaic power generation units; Taking the probit values of the multiple photovoltaic power generation units as independent variables and the efficiency rank sum ratio of the multiple photovoltaic power generation units as dependent variables, calculate the regression equation between the efficiency rank sum ratio and the probit values; Determine the estimated value of the efficiency rank sum ratio of the multiple photovoltaic power generation units according to the regression program; According to the estimated value of the efficiency rank sum ratio of the multiple photovoltaic power generation units, perform high and low score grading on the power generation efficiency of the multiple photovoltaic power generation units to obtain the high and low conditions of the power generation efficiency of the multiple photovoltaic power generation units.

10. The method according to claim 9, characterized in that further includes: According to the high and low conditions of the power generation efficiency of the multiple photovoltaic power generation units, send a prompt message to the monitoring device of the photovoltaic power generation unit whose power generation efficiency is graded as low power generation efficiency, so as to remind the maintenance personnel of the photovoltaic power generation unit with low power generation efficiency to perform maintenance on the photovoltaic power generation unit with low power generation efficiency.

11. The method according to claim 7, characterized in that the benefit type characteristics of the power time series curve include: the cumulative power of the target photovoltaic power generation unit corresponding to the power time series curve within the target duration; the cost type characteristics of the power time series curve include: the average curvature of the power time series curve, and / or, the characterization information of the concavity and convexity change frequency of the power time series curve.

12. A power generation efficiency detection method applicable to a cloud server, characterized in that the method includes: In response to a request for invoking a target service, determine processing resources corresponding to the target service; Execute the steps in the method according to any one of claims 1-11 by using the processing resources corresponding to the target service.

13. An electronic device, characterized in that, comprising: a memory and a processor; wherein the memory is configured to store a computer program; the processor is coupled to the memory and configured to execute the computer program to execute the steps in the method according to any one of claims 1-11.

14. A computer-readable storage medium storing computer instructions, characterized in that, when the computer instructions are executed by one or more processors, the one or more processors are caused to execute the steps in the method according to any one of claims 1-11.

Images