A remote monitoring method for photovoltaic power generation system based on Internet of Things

Abstract

The present invention relates to the field of photovoltaic power generation technology, and specifically discloses a remote monitoring method for a photovoltaic power generation system based on the Internet of Things, including: obtaining the position data of photovoltaic components in the photovoltaic power generation system, screening out abnormal photovoltaic components with abnormal power generation according to the position data of photovoltaic components in the photovoltaic power generation system; obtaining image data of abnormal photovoltaic components, determining the fault type of abnormal photovoltaic components according to the image data of abnormal photovoltaic components; determining an early warning scheme for the photovoltaic power generation system according to the fault type of abnormal photovoltaic components, and monitoring and warning according to the early warning scheme for the photovoltaic power generation system. The present invention can issue early warnings for abnormal situations in a timely manner by monitoring the abnormal situations of photovoltaic components in the photovoltaic power generation system and determining the fault types, thereby ensuring the stable operation of the photovoltaic power generation system.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic power generation technology, and more specifically, to a photovoltaic power generation system remote monitoring method based on the Internet of Things. Background Art

[0002] Photovoltaic power generation system is a power generation system that uses solar cells to directly convert solar energy into electrical energy. Its main components are photovoltaic modules, batteries, controllers and inverters. Its characteristics are high reliability, long service life, no pollution to the environment, independent power generation and grid-connected operation. It is favored by enterprises and organizations in various countries and has broad development prospects. With the awareness of sustainable development being deeply rooted in people's hearts all over the world, the scale of comprehensive utilization of photovoltaic power generation in the world has expanded rapidly, the technology has been continuously developed, and the cost has been significantly reduced, showing a good development prospect. Many countries regard photovoltaic power generation as a key new industry, and photovoltaic power generation has been more widely used.

[0003] With the rise of Internet of Things technology, remote monitoring systems based on the Internet of Things have gradually become an emerging technology for monitoring photovoltaic power generation systems. However, the monitoring of photovoltaic power generation systems in existing technologies is limited to basic data recording and display, and it is impossible to conduct in-depth analysis of the power generation status of photovoltaic modules, and it is impossible to issue early warnings for fault types in a timely manner, resulting in the inability of photovoltaic power generation systems to operate stably. Summary of the invention

[0004] The present invention provides a remote monitoring method for a photovoltaic power generation system based on the Internet of Things, which is used to solve the problem of low monitoring efficiency of the photovoltaic power generation system in the prior art, and comprises:

[0005] Acquire the location data of photovoltaic modules in the photovoltaic power generation system, and screen out abnormal photovoltaic modules with abnormal power generation according to the location data of photovoltaic modules in the photovoltaic power generation system;

[0006] Acquire image data of the abnormal photovoltaic component, and determine the fault type of the abnormal photovoltaic component according to the image data of the abnormal photovoltaic component;

[0007] Determine the early warning plan for the photovoltaic power generation system according to the fault type of the abnormal photovoltaic component, and perform monitoring and early warning according to the early warning plan for the photovoltaic power generation system.

[0008] Furthermore, the step of screening out abnormal photovoltaic components with abnormal power generation according to the location data of the photovoltaic components in the photovoltaic power generation system includes:

[0009] Obtaining meteorological data of the geographical location where the photovoltaic power generation system is located, and determining the light intensity according to the meteorological data of the geographical location where the photovoltaic power generation system is located;

[0010] Obtain the location data of the photovoltaic modules in the photovoltaic power generation system, and determine the effective illumination time of the photovoltaic modules at each location according to the meteorological data of the geographical location of the photovoltaic power generation system;

[0011] The theoretical power generation of the photovoltaic modules is calculated according to the effective illumination time and illumination intensity of the photovoltaic modules at each position, and the theoretical power generation curve is drawn according to the theoretical power generation of the photovoltaic modules;

[0012] The fluctuation coefficient of the photovoltaic modules is determined according to the theoretical power generation variation curve, and the abnormal photovoltaic modules with abnormal power generation are screened out according to the fluctuation coefficient of the photovoltaic modules.

[0013] Furthermore, the method of determining the effective illumination time of the photovoltaic components at each location according to the meteorological data of the geographical location of the photovoltaic power generation system includes:

[0014] Determine the sun's motion trajectory at the location where the photovoltaic power generation system is located according to the meteorological data at the location where the photovoltaic power generation system is located, and establish a sun's motion trajectory model according to the sun's motion trajectory at the location where the photovoltaic power generation system is located;

[0015] The location data of the photovoltaic modules are input into the solar trajectory model to obtain the effective illumination time of the photovoltaic modules at each location.

[0016] Further, determining the fluctuation coefficient of the photovoltaic module according to the theoretical power generation variation curve includes:

[0017] Obtain the actual power generation change curve of the photovoltaic module in a power generation cycle, calculate the difference between the theoretical power generation change curve and the actual power generation change curve in the corresponding period, and obtain the power generation deviation curve;

[0018] The peak value and the trough value in the power generation deviation curve are selected, and the first trough, the peak value and the second trough in the power generation deviation curve are divided into a change cycle to obtain the change cycle of the power generation deviation curve;

[0019] Calculate the absolute value of a first slope from a first trough to a wave peak and the absolute value of a second slope from a wave peak to a second trough within a change cycle, and obtain the sum of the absolute value of the first slope and the absolute value of the second slope;

[0020] The reciprocal of the sum of the absolute value of the first slope and the absolute value of the second slope is taken as the fluctuation time coefficient, and the peak value within the variation period is multiplied by the corresponding fluctuation time coefficient to obtain the period fluctuation coefficient;

[0021] The average periodic fluctuation coefficient of all change periods in the power generation deviation curve is calculated to obtain the fluctuation coefficient of the photovoltaic module.

[0022] Furthermore, the step of screening out abnormal photovoltaic components with abnormal power generation according to the fluctuation coefficient of the photovoltaic components includes:

[0023] The average power generation of the photovoltaic module in a power generation cycle is determined according to the actual power generation change curve, and the inverse of the fluctuation coefficient is normalized and multiplied by the average power generation to obtain the power generation coefficient of the photovoltaic module;

[0024] Obtaining a preset power generation coefficient threshold, and determining whether a difference between the power generation coefficient of the photovoltaic module and the preset power generation coefficient threshold is greater than a first preset threshold;

[0025] If the difference between the power generation coefficient of the photovoltaic module and the preset power generation coefficient threshold is greater than the first preset threshold, the corresponding photovoltaic module is determined as a normal photovoltaic module;

[0026] If the difference between the power generation coefficient of the photovoltaic component and the preset power generation coefficient threshold is less than or equal to the first preset threshold, the corresponding photovoltaic component is determined as an abnormal photovoltaic component.

[0027] Further, the determining the fault type of the abnormal photovoltaic component according to the image data of the abnormal photovoltaic component includes:

[0028] Determine the abnormal period according to the actual power generation change curve of the abnormal photovoltaic component, and obtain image data of the abnormal photovoltaic component in the abnormal period;

[0029] Grayscale processing is performed on the image data of the abnormal photovoltaic component in the abnormal period to obtain an abnormal grayscale image;

[0030] Segmenting the abnormal grayscale image to obtain multiple abnormal image blocks;

[0031] Calculate the grayscale value of each abnormal image block, set the central image block in order, filter out the deviation image block according to the grayscale values ​​of the central image block and the abnormal image blocks within the 8-neighborhood range, and determine the fault type according to the grayscale value of the deviation image block.

[0032] Furthermore, the determining of the abnormal period according to the actual power generation variation curve of the abnormal photovoltaic module includes:

[0033] According to the actual power generation change curve of the abnormal photovoltaic assembly, the time period when the actual power generation of the abnormal photovoltaic assembly is less than the second preset threshold is selected, and the time period when the actual power generation of the abnormal photovoltaic assembly is less than the second preset threshold is set as the abnormal time period;

[0034] Or, according to the theoretical power generation change curve of the abnormal photovoltaic panel, the time period when the periodic fluctuation coefficient of the abnormal photovoltaic component is greater than the third preset threshold is screened out, and the time period when the periodic fluctuation coefficient of the abnormal photovoltaic component is greater than the third preset threshold is set as the abnormal time period.

[0035] Furthermore, the step of filtering out the deviation image block according to the grayscale values ​​of the central image block and the abnormal image blocks within the 8-neighborhood range includes:

[0036] Calculating a deviation value of the central image block according to a deviation value calculation formula, and determining a central image block whose deviation value is greater than a fourth preset threshold as a deviation image block;

[0037] The specific calculation formula of the deviation value is:

[0038]

[0039] Among them, P is the deviation value, G i is the gray value of the i-th central image block, G avg is the average gray value of all abnormal image blocks within the 8-neighborhood range, G j is the gray value of the jth abnormal image block within the 8-neighborhood range of the central image block.

[0040] Further, determining the fault type according to the grayscale value of the deviation image block includes:

[0041] Calculate the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks in the abnormal grayscale image of the abnormal photovoltaic module, and determine whether the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is greater than a fifth preset threshold;

[0042] If the difference between the grayscale values ​​of the deviation image block and the remaining abnormal image blocks is greater than a fifth preset threshold, it is determined that the fault type of the corresponding abnormal photovoltaic component is a light spot abnormality;

[0043] If the difference between the grayscale values ​​of the deviation image block and the other abnormal image blocks is less than or equal to the fifth preset threshold, determine whether the difference between the grayscale values ​​of the deviation image block and the other abnormal image blocks is greater than a sixth preset threshold;

[0044] If the difference between the grayscale values ​​of the deviation image block and the remaining abnormal image blocks is greater than a sixth preset threshold, it is determined that the fault type of the corresponding abnormal photovoltaic component is building occlusion;

[0045] If the difference in grayscale value between the deviation image block and the remaining abnormal image blocks is less than or equal to the sixth preset threshold, it is determined that the fault type of the corresponding abnormal photovoltaic component is obstruction by an obstacle.

[0046] Furthermore, the method of determining an early warning scheme for a photovoltaic power generation system according to the fault type of an abnormal photovoltaic component includes:

[0047] Obtain the historical fault types and corresponding historical power generation change curves of the photovoltaic power generation system, and establish a model training sample set based on the historical fault types and corresponding historical power generation change curves;

[0048] Establish an early warning plan generation model, train the early warning plan generation model according to the model training sample set, and obtain a trained early warning plan generation model;

[0049] The fault type of abnormal photovoltaic components and the corresponding actual power generation change curve are input into the trained early warning plan generation model to obtain the early warning plan of the photovoltaic power generation system.

[0050] The beneficial effects of the present invention are:

[0051] By applying the above technical scheme, the present invention screens out abnormally generating photovoltaic components by monitoring the power generation of photovoltaic components during the power generation cycle and combining the position data of the photovoltaic components, and accurately locates the abnormal photovoltaic components. At the same time, the fault type is analyzed by collecting image data of the abnormal photovoltaic components, and a corresponding early warning scheme is generated, and early warnings are issued in time for abnormal situations, effectively ensuring the stable operation of the photovoltaic power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0053] Figure 1 The present invention shows a schematic flow chart of a remote monitoring method for a photovoltaic power generation system based on the Internet of Things proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] The present application embodiment provides a remote monitoring method for a photovoltaic power generation system based on the Internet of Things, such as Figure 1 As shown, including:

[0056] S101, obtaining location data of photovoltaic modules in a photovoltaic power generation system, and screening out abnormal photovoltaic modules with abnormal power generation according to the location data of photovoltaic modules in the photovoltaic power generation system.

[0057] In some embodiments of the present application, the method of screening out abnormal photovoltaic components with abnormal power generation according to the position data of photovoltaic components in the photovoltaic power generation system includes: obtaining meteorological data of the geographical location of the photovoltaic power generation system, and determining the light intensity according to the meteorological data of the geographical location of the photovoltaic power generation system; obtaining the position data of photovoltaic components in the photovoltaic power generation system, and determining the effective light time of photovoltaic components at each location according to the meteorological data of the geographical location of the photovoltaic power generation system; calculating the theoretical power generation of the photovoltaic components according to the effective light time and light intensity of the photovoltaic components at each location, and drawing a theoretical power generation change curve according to the theoretical power generation of the photovoltaic components; determining the fluctuation coefficient of the photovoltaic components according to the theoretical power generation change curve, and screening out abnormal photovoltaic components with abnormal power generation according to the fluctuation coefficient of the photovoltaic components.

[0058] In this embodiment, the meteorological data of the geographical location of the photovoltaic power generation system is obtained to obtain the sun's movement trajectory and the light intensity in the corresponding time period. The theoretical power generation of each photovoltaic module is calculated according to the conversion efficiency, light intensity and effective light time of the photovoltaic module. The fluctuation coefficient of the photovoltaic module is calculated based on the theoretical power generation, so as to screen out abnormal photovoltaic modules.

[0059] In some embodiments of the present application, determining the effective illumination time of photovoltaic components at each location based on meteorological data of the geographical location of the photovoltaic power generation system includes: determining the movement trajectory of the sun at the geographical location of the photovoltaic power generation system based on the meteorological data of the geographical location of the photovoltaic power generation system, and establishing a solar trajectory model based on the movement trajectory of the sun at the geographical location of the photovoltaic power generation system; inputting the position data of the photovoltaic components into the solar trajectory model to obtain the effective illumination time of the photovoltaic components at each location.

[0060] In this embodiment, by utilizing the lighting function in 3D animation software such as Blender, Maya, Unity, etc., the sun's rays are projected onto the model surface to simulate the sun's movement process. By setting a timeline and establishing a solar trajectory model based on the sun's movement trajectory, the position data of the photovoltaic components are input into the solar trajectory model to simulate the effective lighting time of each photovoltaic component.

[0061] In some embodiments of the present application, the method of determining the fluctuation coefficient of the photovoltaic module based on the theoretical power generation change curve includes: obtaining the actual power generation change curve of the photovoltaic module within a power generation cycle, calculating the difference between the theoretical power generation change curve and the actual power generation change curve in the corresponding time period, and obtaining the power generation deviation curve; screening out the peak value and trough value in the power generation deviation curve, dividing the first trough, the peak and the second trough in the power generation deviation curve into a change cycle, and obtaining the change cycle of the power generation deviation curve; calculating the absolute value of the first slope from the first trough to the peak and the absolute value of the second slope from the peak to the second trough in a change cycle, and obtaining the sum of the absolute value of the first slope and the absolute value of the second slope; taking the reciprocal of the sum of the absolute value of the first slope and the absolute value of the second slope as the fluctuation time coefficient, multiplying the peak value in the change cycle by the corresponding fluctuation time coefficient, and obtaining the periodic fluctuation coefficient; calculating the average periodic fluctuation coefficient of all change cycles in the power generation deviation curve to obtain the fluctuation coefficient of the photovoltaic module.

[0062] In this embodiment, the actual power generation of the photovoltaic module in a power generation cycle is collected to draw the actual power generation change curve, and the power generation of the theoretical power generation change curve is subtracted from the power generation of the actual power generation change curve in the corresponding period, so as to draw the power generation deviation curve, and the two adjacent troughs of the power generation deviation curve are respectively set as the first trough and the second trough, and the peak between the two adjacent troughs is combined to complete the division of a change cycle. The larger the sum of the absolute values ​​of the slopes in a change cycle, the faster the speed of restoring stability of the power generation deviation is, and the smaller the fluctuation time coefficient is.

[0063] In some embodiments of the present application, the method of screening out abnormal photovoltaic components with abnormal power generation according to the fluctuation coefficient of the photovoltaic components includes: determining the average power generation of the photovoltaic components in a power generation cycle according to the actual power generation change curve, normalizing the inverse of the fluctuation coefficient and multiplying it by the average power generation to obtain the power generation coefficient of the photovoltaic components; obtaining a preset power generation coefficient threshold, and determining whether the difference between the power generation coefficient of the photovoltaic component and the preset power generation coefficient threshold is greater than a first preset threshold; if the difference between the power generation coefficient of the photovoltaic component and the preset power generation coefficient threshold is greater than the first preset threshold, determining the corresponding photovoltaic component as a normal photovoltaic component; if the difference between the power generation coefficient of the photovoltaic component and the preset power generation coefficient threshold is less than or equal to the first preset threshold, determining the corresponding photovoltaic component as an abnormal photovoltaic component.

[0064] In this embodiment, the range of the inverse of the fluctuation coefficient is limited to between 0 and 1 through normalization processing, so as to calculate the power generation coefficient of the photovoltaic module, and the photovoltaic module whose power generation coefficient has a difference with the preset power generation coefficient threshold that is less than or equal to the first preset threshold is determined as an abnormal photovoltaic module.

[0065] S102, acquiring image data of an abnormal photovoltaic component, and determining a fault type of the abnormal photovoltaic component according to the image data of the abnormal photovoltaic component.

[0066] In some embodiments of the present application, determining the fault type of the abnormal photovoltaic component based on the image data of the abnormal photovoltaic component includes: determining the abnormal time period based on the actual power generation change curve of the abnormal photovoltaic component, and obtaining the image data of the abnormal photovoltaic component in the abnormal time period; graying the image data of the abnormal photovoltaic component in the abnormal time period to obtain an abnormal grayscale image; segmenting the abnormal grayscale image to obtain a plurality of abnormal image blocks; calculating the grayscale value of each abnormal image block, setting the central image block in sequence, filtering out the deviation image block according to the grayscale values ​​of the central image block and the abnormal image blocks within the 8-neighborhood range, and determining the fault type according to the grayscale value of the deviation image block.

[0067] In this embodiment, any clear image data of the abnormal photovoltaic component within the abnormal period is collected, and the preset size of the segmented abnormal image block is set according to the size of the abnormal grayscale image. The abnormal grayscale image is segmented into a number of square abnormal image blocks according to the preset size. The grayscale value of each abnormal image block is the average grayscale of the abnormal image block. Each abnormal image block is set as a central image block in order from left to right and from top to bottom, so as to screen out the deviation image block and obtain the fault type.

[0068] In some embodiments of the present application, determining the abnormal time period according to the actual power generation change curve of the abnormal photovoltaic component includes: screening out the time period when the actual power generation of the abnormal photovoltaic component is less than a second preset threshold value according to the actual power generation change curve of the abnormal photovoltaic component, and setting the time period when the actual power generation of the abnormal photovoltaic panel is less than the second preset threshold value as the abnormal time period; or screening out the time period when the periodic fluctuation coefficient of the abnormal photovoltaic component is greater than a third preset threshold value according to the theoretical power generation change curve of the abnormal photovoltaic panel, and setting the time period when the periodic fluctuation coefficient of the abnormal photovoltaic component is greater than the third preset threshold value as the abnormal time period.

[0069] In this embodiment, by setting the abnormal time period through the actual power generation of the abnormal photovoltaic component or the periodic fluctuation coefficient, the time period when the power generation of the abnormal photovoltaic component is abnormal can be accurately located, which facilitates the extraction of abnormal images.

[0070] In some embodiments of the present application, the method of screening out the deviation image block according to the grayscale values ​​of the central image block and the abnormal image block within the 8-neighborhood range includes: calculating the deviation value of the central image block according to a deviation value calculation formula, and determining the central image block whose deviation value is greater than a fourth preset threshold as the deviation image block; the deviation value calculation formula is specifically,

[0071]

[0072] Among them, P is the deviation value, G i is the gray value of the i-th central image block, G avg is the average gray value of all abnormal image blocks within the 8-neighborhood range, G j is the gray value of the jth abnormal image block within the 8-neighborhood range of the central image block.

[0073] In this embodiment, by calculating the deviation value of each abnormal image block, the deviation between the abnormal image block and surrounding abnormal image blocks is calculated, thereby screening out deviation image blocks whose deviation values ​​are greater than a fourth preset threshold.

[0074] In some embodiments of the present application, determining the fault type according to the grayscale value of the deviation image block includes: calculating the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks in the abnormal grayscale image of the abnormal photovoltaic component, and judging whether the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is greater than a fifth preset threshold; if the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is greater than the fifth preset threshold, judging that the fault type of the corresponding abnormal photovoltaic component is a light spot abnormality; if the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is less than or equal to the fifth preset threshold, judging whether the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is greater than a sixth preset threshold; if the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is greater than the sixth preset threshold, judging that the fault type of the corresponding abnormal photovoltaic component is building obstruction; if the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is less than or equal to the sixth preset threshold, judging that the fault type of the corresponding abnormal photovoltaic component is obstacle obstruction.

[0075] In this embodiment, the grayscale values ​​of the remaining abnormal image blocks are the average grayscale values ​​of the abnormal grayscale images except the deviation image block, the fifth preset threshold is a positive number slightly greater than 0, and the sixth preset threshold is 0. When the difference in grayscale value between the deviation image block and the remaining abnormal image blocks is greater than the fifth preset threshold, it indicates that the grayscale value of the deviation image block is much greater than the grayscale values ​​of the remaining abnormal image blocks, and the fault type of the corresponding abnormal photovoltaic component is judged to be light spot abnormality; when the difference in grayscale value between the deviation image block and the remaining abnormal image blocks is greater than the sixth preset threshold, it indicates that the grayscale value of the deviation image block is not much different from the grayscale value of the remaining abnormal image blocks, and therefore the fault type of the corresponding abnormal photovoltaic component is judged to be large-area building occlusion; when the difference in grayscale value between the deviation image block and the remaining abnormal image blocks is less than or equal to the sixth preset threshold, it indicates that the grayscale value of the deviation image block is less than the grayscale value of the remaining abnormal image blocks, and therefore the fault type of the corresponding abnormal photovoltaic component is judged to be small-area obstacle occlusion.

[0076] S103, determining an early warning plan for the photovoltaic power generation system according to the fault type of the abnormal photovoltaic component, and performing monitoring and early warning according to the early warning plan for the photovoltaic power generation system.

[0077] In some embodiments of the present application, determining an early warning plan for a photovoltaic power generation system based on the fault type of an abnormal photovoltaic component includes: obtaining historical fault types and corresponding historical power generation change curves of the photovoltaic power generation system, and establishing a model training sample set based on the historical fault types and the corresponding historical power generation change curves; establishing an early warning plan generation model, and training the early warning plan generation model based on the model training sample set to obtain a trained early warning plan generation model; inputting the fault type of the abnormal photovoltaic component and the corresponding actual power generation change curve into the trained early warning plan generation model to obtain an early warning plan for the photovoltaic power generation system.

[0078] In this embodiment, an early warning scheme generation model is established based on a deep learning neural network, and the early warning scheme generation model is trained through the historical fault types of the photovoltaic power generation system and the corresponding historical power generation change curves, so as to generate an early warning scheme for the photovoltaic power generation system according to the fault types of abnormal photovoltaic components and the corresponding actual power generation change curves. At the same time, the photovoltaic power generation system is warned according to the early warning scheme, so that operation and maintenance personnel can accurately formulate operation and maintenance plans according to the early warning scheme to ensure the stable operation of the photovoltaic power generation system.

[0079] By applying the above technical solutions, the present invention obtains the position data of photovoltaic modules in the photovoltaic power generation system, and screens out abnormal photovoltaic modules with abnormal power generation according to the position data of photovoltaic modules in the photovoltaic power generation system; obtains image data of abnormal photovoltaic modules, and determines the fault type of abnormal photovoltaic modules according to the image data of abnormal photovoltaic modules; determines the early warning scheme of the photovoltaic power generation system according to the fault type of abnormal photovoltaic modules, and monitors and warns according to the early warning scheme of the photovoltaic power generation system. The present invention can issue early warnings for abnormal situations in a timely manner by monitoring the abnormal situations of photovoltaic modules in the photovoltaic power generation system and determining the fault types, thereby ensuring the stable operation of the photovoltaic power generation system.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A remote monitoring method for a photovoltaic power generation system based on the Internet of Things, characterized in that: include: Acquire the location data of photovoltaic modules in the photovoltaic power generation system, and screen out abnormal photovoltaic modules with abnormal power generation according to the location data of photovoltaic modules in the photovoltaic power generation system; Acquire image data of the abnormal photovoltaic component, and determine the fault type of the abnormal photovoltaic component according to the image data of the abnormal photovoltaic component; Determine the early warning plan for the photovoltaic power generation system according to the fault type of the abnormal photovoltaic component, and perform monitoring and early warning according to the early warning plan for the photovoltaic power generation system.

2. The remote monitoring method for photovoltaic power generation system based on Internet of Things according to claim 1 is characterized in that: The method of screening out abnormal photovoltaic components with abnormal power generation according to the location data of the photovoltaic components in the photovoltaic power generation system includes: Obtaining meteorological data of the geographical location where the photovoltaic power generation system is located, and determining the light intensity according to the meteorological data of the geographical location where the photovoltaic power generation system is located; Obtain the location data of the photovoltaic modules in the photovoltaic power generation system, and determine the effective illumination time of the photovoltaic modules at each location according to the meteorological data of the geographical location of the photovoltaic power generation system; The theoretical power generation of the photovoltaic modules is calculated according to the effective illumination time and illumination intensity of the photovoltaic modules at each position, and the theoretical power generation curve is drawn according to the theoretical power generation of the photovoltaic modules; The fluctuation coefficient of the photovoltaic modules is determined according to the theoretical power generation variation curve, and the abnormal photovoltaic modules with abnormal power generation are screened out according to the fluctuation coefficient of the photovoltaic modules.

3. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 2 is characterized in that: The method of determining the effective illumination time of photovoltaic components at each location according to the meteorological data of the geographical location of the photovoltaic power generation system comprises: Determine the sun's motion trajectory at the location where the photovoltaic power generation system is located according to the meteorological data at the location where the photovoltaic power generation system is located, and establish a sun's motion trajectory model according to the sun's motion trajectory at the location where the photovoltaic power generation system is located; The location data of the photovoltaic modules are input into the solar trajectory model to obtain the effective illumination time of the photovoltaic modules at each location.

4. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 2 is characterized in that: The method of determining the fluctuation coefficient of the photovoltaic module according to the theoretical power generation variation curve includes: Obtain the actual power generation change curve of the photovoltaic module in a power generation cycle, calculate the difference between the theoretical power generation change curve and the actual power generation change curve in the corresponding period, and obtain the power generation deviation curve; The peak value and the trough value in the power generation deviation curve are selected, and the first trough, the peak value and the second trough in the power generation deviation curve are divided into a change cycle to obtain the change cycle of the power generation deviation curve; Calculate the absolute value of a first slope from a first trough to a wave peak and the absolute value of a second slope from a wave peak to a second trough within a change cycle, and obtain the sum of the absolute value of the first slope and the absolute value of the second slope; The reciprocal of the sum of the absolute value of the first slope and the absolute value of the second slope is taken as the fluctuation time coefficient, and the peak value within the variation period is multiplied by the corresponding fluctuation time coefficient to obtain the period fluctuation coefficient; The average periodic fluctuation coefficient of all change periods in the power generation deviation curve is calculated to obtain the fluctuation coefficient of the photovoltaic module.

5. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 4 is characterized in that: The method of screening out abnormal photovoltaic components with abnormal power generation according to the fluctuation coefficient of the photovoltaic components includes: The average power generation of the photovoltaic module in a power generation cycle is determined according to the actual power generation change curve, and the inverse of the fluctuation coefficient is normalized and multiplied by the average power generation to obtain the power generation coefficient of the photovoltaic module; Obtaining a preset power generation coefficient threshold, and determining whether a difference between the power generation coefficient of the photovoltaic module and the preset power generation coefficient threshold is greater than a first preset threshold; If the difference between the power generation coefficient of the photovoltaic module and the preset power generation coefficient threshold is greater than the first preset threshold, the corresponding photovoltaic module is determined as a normal photovoltaic module; If the difference between the power generation coefficient of the photovoltaic component and the preset power generation coefficient threshold is less than or equal to the first preset threshold, the corresponding photovoltaic component is determined as an abnormal photovoltaic component.

6. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 5 is characterized in that: The method of determining the fault type of the abnormal photovoltaic component according to the image data of the abnormal photovoltaic component comprises: Determine the abnormal period according to the actual power generation change curve of the abnormal photovoltaic component, and obtain image data of the abnormal photovoltaic component in the abnormal period; Grayscale processing is performed on the image data of the abnormal photovoltaic module in the abnormal period to obtain an abnormal grayscale image; Segmenting the abnormal grayscale image to obtain multiple abnormal image blocks; Calculate the grayscale value of each abnormal image block, set the central image block in order, filter out the deviation image block according to the grayscale values ​​of the central image block and the abnormal image blocks within the 8-neighborhood range, and determine the fault type according to the grayscale value of the deviation image block.

7. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 6 is characterized in that: The determining of the abnormal period according to the actual power generation change curve of the abnormal photovoltaic assembly includes: According to the actual power generation change curve of the abnormal photovoltaic assembly, the time period when the actual power generation of the abnormal photovoltaic assembly is less than the second preset threshold is selected, and the time period when the actual power generation of the abnormal photovoltaic assembly is less than the second preset threshold is set as the abnormal time period; Or, according to the theoretical power generation change curve of the abnormal photovoltaic panel, the time period when the periodic fluctuation coefficient of the abnormal photovoltaic component is greater than the third preset threshold is screened out, and the time period when the periodic fluctuation coefficient of the abnormal photovoltaic component is greater than the third preset threshold is set as the abnormal time period.

8. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 6 is characterized in that: The step of screening out the deviation image block according to the grayscale values ​​of the central image block and the abnormal image blocks within the 8-neighborhood range includes: Calculating a deviation value of the central image block according to a deviation value calculation formula, and determining a central image block whose deviation value is greater than a fourth preset threshold as a deviation image block; The specific calculation formula of the deviation value is: Among them, P is the deviation value, G i is the gray value of the i-th central image block, G avg is the average gray value of all abnormal image blocks within the 8-neighborhood range, G j is the gray value of the jth abnormal image block within the 8-neighborhood range of the central image block.

9. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 8, characterized in that: The step of determining the fault type according to the grayscale value of the deviation image block includes: Calculate the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks in the abnormal grayscale image of the abnormal photovoltaic module, and determine whether the difference in grayscale values ​​between the deviation image block and the remaining abnormal image blocks is greater than a fifth preset threshold; If the difference between the grayscale values ​​of the deviation image block and the remaining abnormal image blocks is greater than a fifth preset threshold, it is determined that the fault type of the corresponding abnormal photovoltaic component is a light spot abnormality; If the difference between the grayscale values ​​of the deviation image block and the other abnormal image blocks is less than or equal to the fifth preset threshold, determine whether the difference between the grayscale values ​​of the deviation image block and the other abnormal image blocks is greater than a sixth preset threshold; If the difference between the grayscale values ​​of the deviation image block and the remaining abnormal image blocks is greater than a sixth preset threshold, it is determined that the fault type of the corresponding abnormal photovoltaic component is building occlusion; If the difference in grayscale value between the deviation image block and the remaining abnormal image blocks is less than or equal to the sixth preset threshold, it is determined that the fault type of the corresponding abnormal photovoltaic component is obstruction by an obstacle.

10. The remote monitoring method of photovoltaic power generation system based on Internet of Things according to claim 9, characterized in that: The method of determining an early warning scheme for a photovoltaic power generation system according to the fault type of an abnormal photovoltaic component comprises: Obtain the historical fault types and corresponding historical power generation change curves of the photovoltaic power generation system, and establish a model training sample set based on the historical fault types and corresponding historical power generation change curves; Establish an early warning plan generation model, train the early warning plan generation model according to the model training sample set, and obtain a trained early warning plan generation model; The fault type of abnormal photovoltaic components and the corresponding actual power generation change curve are input into the trained early warning plan generation model to obtain the early warning plan of the photovoltaic power generation system.

Images