Photovoltaic intelligent cleaning method and device based on power generation capacity prediction and storage medium

Abstract

The invention relates to the technical field of photovoltaic cleaning, in particular to a photovoltaic intelligent cleaning method and device based on power generation capacity prediction and a storage medium. The method comprises the steps that in a target detection area of a solar cell panel, according to a dust deposition light transmittance variable, an influence degree variable of non-dust deposition dirt on light absorption, current environment characteristics and parameters of a clean solar cell panel string, the predicted generating capacity of each string in each time period is predicted; after the iteration of the plurality of time periods is completed, summarizing the ash deposition light transmittance variables of the plurality of time periods and the influence degree variables of the plurality of time periods; if a set number of ash deposition light transmittance variables are greater than a set threshold value, determining that the corresponding string is of an ash deposition type; determining the corresponding string as an easy-to-clean type or a difficult-to-clean type according to the change trend; and cleaning the string according to the ash deposition type, the easy-to-clean type or the difficult-to-clean type of the string. According to the invention, different dirt types and cleaning modes can be determined.

Description

Technical Field

[0001] The present application relates to the field of photovoltaic cleaning technology. Specifically, it relates to a photovoltaic intelligent cleaning method, device, and storage medium based on power generation prediction. Background Art

[0002] A solar panel is a device that converts solar energy into electrical energy, mainly made of semiconductor materials such as silicon. When sunlight shines on the surface of the panel, photons excite electrons to generate an electric current, thereby achieving photovoltaic conversion. It is necessary to clean the solar panel to ensure its normal operation. Dust, dirt, etc. will block sunlight and reduce the power generation efficiency of the panel. Regular cleaning can ensure that the panel fully absorbs sunlight and maintains high-efficiency power generation. Dirt may corrode the surface of the panel and affect its lifespan. Cleaning can reduce corrosion and extend the service time of the equipment. The accumulation of dirt may cause the temperature in some areas to be too high, forming hot spots and damaging the panel. Cleaning can avoid this problem.

[0003] Currently, due to the large coverage area of solar panels, cameras are arranged around the solar panels in some areas, and image detection technology is used to determine whether the panel needs to be cleaned. When cleaning is required, robots or personnel are sent to clean the panel.

[0004] However, the existing image detection technology can only determine whether the panel needs to be cleaned, but it is difficult to determine the degree of pollution and the cleaning method to be adopted. In view of this, the present application provides a photovoltaic intelligent cleaning solution relying on power generation. Summary of the Invention

[0005] The purpose of the present application is to provide a photovoltaic intelligent cleaning method, device, and storage medium based on power generation prediction to make up for the defects of image detection.

[0006] To achieve the above purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a photovoltaic intelligent cleaning method based on power generation prediction, including:

[0008] Within the target detection area of the solar panel, according to the variable of dust accumulation light transmittance, the variable of the influence degree of non-dust dirt on light absorption, as well as the current environmental characteristics and the parameters of the solar panel string to be cleaned, predict the predicted power generation of each string in each time period.

[0009] Obtain the actual power generation of each string in each time period.

[0010] Iterate the dust accumulation light transmittance variable and the influence degree variable in each time period to minimize the gap between the predicted power generation and the actual power generation of each string, and obtain the dust accumulation light transmittance variable and the influence degree variable in each time period; during the iteration process in the same time period, the difference in the dust accumulation light transmittance variables of different strings in the same area is less than the set value; during the iteration process in adjacent time periods, the dust accumulation light transmittance of the same string in the latter time period is less than that in the previous time period;

[0011] After completing the iteration of multiple time periods, summarize the dust accumulation light transmittance variables of multiple time periods and the influence degree variables of multiple time periods;

[0012] If there are a set number of dust accumulation light transmittance variables greater than the set threshold among the dust accumulation light transmittance variables of multiple time periods, determine the corresponding string as the dust accumulation type;

[0013] Determine the change trend of the influence degree variable of each string according to the chronological order, and determine the corresponding string as the easy-to-clean type or the difficult-to-clean type according to the change trend;

[0014] Clean the strings according to the dust accumulation type, easy-to-clean type or difficult-to-clean type of the strings.

[0015] Optionally, predict the predicted power generation of each string in each time period according to the dust accumulation light transmittance variable, the influence degree variable of non-dust accumulation dirt on light absorption, the current environmental characteristics and the parameters of cleaning the solar panel strings, including:

[0016] Calculate the predicted power generation P of each string in each time period according to the following formula:

[0017]

[0018] where G is the light intensity, A is the area of the panel string, η is the photoelectric conversion efficiency, and the range is 0 to 1; t represents the duration of the time period, R is the original reflectivity of the panel surface, and the range is 0 to 1; σ is the dust accumulation light transmittance variable, and the range is 0 to 1; τ is the proportion of the dust accumulation area, and the fixed value 1 is taken; δ is the influence degree variable of non-dust accumulation dirt on light absorption, which represents the result of adding the products of the reciprocal of the light transmittance of each non-dust accumulation dirt and the area proportion.

[0019] Optionally, determine the change trend of the influence degree variable of each string according to the chronological order, and determine the corresponding string as the easy-to-clean type or the difficult-to-clean type, including:

[0020] If the influence degree variable of the same string increases with time, determine the string as the difficult-to-clean type;

[0021] If the influence degree variable of the same string oscillates up and down or decreases with time, determine the string as the easy-to-clean type.

[0022] Optionally, according to the dust accumulation type, easy-to-clean type or difficult-to-clean type of the string, the string is cleaned, including:

[0023] If the string is of the dust accumulation type, the string is cleaned with clean water;

[0024] If the string is of the easy-to-clean type, it is cleaned with a scraper and clean water;

[0025] If the string is of the difficult-to-clean type, it is cleaned with clean water, a cleaning agent and a flexible brush.

[0026] Optionally, after cleaning the string, it further includes: returning to the operation of predicting the predicted power generation of each string in each time period.

[0027] In a second aspect, the present application provides an electronic device, including:

[0028] At least one processor, and a memory communicatively connected to at least one of the processors;

[0029] Wherein, the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute any one of the photovoltaic intelligent cleaning methods based on power generation prediction.

[0030] In a third aspect, the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause the computer to execute any one of the photovoltaic intelligent cleaning methods based on power generation prediction.

[0031] Compared with the prior art, the beneficial effects of the present application are:

[0032] In the embodiments of the present application, according to the different areas occupied by the dirt, the dust accumulation occupying the entire area of the solar panel is divided out, and the non-dust accumulation dirt occupying a part of the area of the solar panel is divided out, and a prediction method for power generation is constructed. Then, by predicting that the power generation approaches the actual power generation, the dust accumulation light transmittance variable and the influence degree variable of the non-dust accumulation dirt are iterated. In this way, the change trend of the dust accumulation on the solar panel and the change trend of the non-dust accumulation dirt can be obtained respectively, so as to determine different types and cleaning methods. When iterating the dust accumulation light transmittance variable, this embodiment adopts spatial constraint conditions and time constraint conditions, that is, the dust accumulation light transmittance variables of different strings vary little, and the dust accumulation of the same string thickens over time, and the dust accumulation light transmittance becomes smaller and smaller. This iterative method is closer to the actual situation, and the change law of the non-dust accumulation dirt can also be successfully determined by means of the change law of the dust accumulation. Description of the Drawings

[0033] To more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the accompanying drawings required for the description of the specific embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0034] Figure 1 is a schematic flowchart of a photovoltaic intelligent cleaning method based on power generation prediction provided by an embodiment of the present application;

[0035] Figure 2 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specific Embodiments

[0036] The following describes exemplary embodiments of the present application with reference to the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. It should be considered that they are merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description below omits the description of well-known functions and structures.

[0037] The solution provided by the embodiment of the present application is used to determine the dirt type of the solar panels and the cleaning difficulty level according to the power generation prediction technology, so as to adapt to different cleaning methods. This embodiment only needs to perform power generation prediction and use the big data of multiple panel strings to distinguish the ash accumulation type, easy-to-clean type or difficult-to-clean type of the strings, and clean the strings, without the participation of sensors such as cameras.

[0038] Figure 1 is a flowchart of a photovoltaic intelligent cleaning method based on power generation prediction provided by this embodiment, and this method can be executed by an electronic device. As Figure 1 shown, this method includes the following steps:

[0039] S110. In the target detection area of the solar panels, predict the predicted power generation of each string at each time period according to the ash accumulation light transmittance variable, the influence degree variable of non-ash dirt on light absorption, as well as the current environmental characteristics and the parameters of cleaning the solar panel strings.

[0040] The target detection area can be the entire geographical area occupied by the solar panels, and there are multiple solar panel strings (hereinafter referred to as strings) therein. The power generation of each string is predicted as a unit.

[0041] Optionally, calculate the predicted power generation P of each string at each time period according to the following formula:

[0042]

[0043] Wherein, G is the light intensity, A is the area of the PV module string, η is the photoelectric conversion efficiency, with a range of 0 to 1; t represents the duration of the time period (such as half an hour or one hour), R represents the original reflectivity of the PV module surface, with a range of 0 to 1; σ is the variable of the dust transmittance, with a range of 0 to 1. The more severe the dust accumulation, the lower the dust transmittance and the lower the power generation; τ is the proportion of the dust-covered area, taking a fixed value of 1; δ is the variable of the influence degree of non-dust dirt on light absorption, representing the result of adding the products of the reciprocal of the transmittance of each non-dust dirt and its area proportion. For example, there is the following formula:

[0044]

[0045] Wherein, σ n represents the transmittance of the nth type of non-dust dirt, and τ n is the area proportion of the nth type of non-dust dirt on the PV module. In this embodiment, the types and area proportions of non-dust dirt are not distinguished. Only the foregoing formula (2) of various non-dust dirt and its area proportion are integrated to obtain the variable of the influence degree of non-dust dirt on light absorption. This variable is a value between 0 and 1. The larger the value, the lower the power generation. Based on this, in the foregoing formula (1), represents the influence on power generation compared with a clean PV module when the PV module has dust accumulation and non-dust dirt. This value is between 0 and 1. The smaller the value, the lower the power generation.

[0046] S120. Obtain the actual power generation of each string in each time period.

[0047] Each string is connected with an ammeter, a voltmeter, a wattmeter, etc. Then, the actual power generation of each string in each time period is obtained according to the readings of these instruments.

[0048] S130. Iterate the dust transmittance variable and the influence degree variable in each time period to minimize the gap between the predicted power generation and the actual power generation of each string, and obtain the dust transmittance variable and the influence degree variable in each time period.

[0049] Before the first iteration, it should be ensured that the PV module has been cleaned and is relatively clean. Then, a relatively large value is assigned to the dust transmittance variable, and a relatively small value is assigned to the influence degree variable. For each time period and each string, a predicted power generation and an actual power generation are obtained. If the gap between the predicted power generation and the actual power generation is greater than the set value, such as 50, the dust transmittance variable and the influence degree variable need to be updated until the gap between the predicted power generation and the actual power generation is less than the set value.

[0050] During the iteration process in the same time period, the following iteration conditions should be met: the difference between the ash accumulation light transmittance variables of different strings in the same area is less than the set value. Here, the area refers to the areas of different terrains divided within the target detection area, such as dividing different areas according to terrain height and slope. There may be some differences in the dust distribution in the spaces of different areas, while the dust distribution in the space of the same area is considered to be consistent, so the ash accumulation rates are considered to be similar. Then, the difference between the ash accumulation light transmittance variables of different strings in the same area in the same time period should be relatively small; while the difference between the ash accumulation light transmittance variables of strings in different areas in the same time period is allowed to be a relatively large value.

[0051] During the iteration process in adjacent time periods, the following iteration conditions should be met: the ash accumulation light transmittance of the same string in the later time period is less than that in the previous time period. For any string, as time goes by, the ash accumulation should gradually thicken and the ash accumulation light transmittance should gradually decrease (in this embodiment, extreme weather such as strong wind, rain and snow is not considered. In fact, the solar panels should be turned off in extreme weather to ensure safety and the power generation is 0).

[0052] For each time period and each string, multiple iterations are required to find the appropriate ash accumulation light transmittance and influence degree variables.

[0053] S140. After completing the iterations of multiple time periods, summarize the ash accumulation light transmittance variables of multiple time periods and the influence degree variables of multiple time periods.

[0054] Through the above operations, the ash accumulation light transmittance and influence degree variables of each string in each time period are obtained. For each string, a time series of ash accumulation light transmittance variables and a time series of influence degree variables are formed in chronological order.

[0055] S150. If there are a set number of ash accumulation light transmittance variables greater than the set threshold among the ash accumulation light transmittance variables of multiple time periods, determine the corresponding string as the ash accumulation type.

[0056] The set number can be determined according to experience. For example, if the ash accumulation light transmittance variables of 30% of the time periods are greater than the set threshold, determine the corresponding string as the ash accumulation type. That is to say, there is ash accumulation on this string.

[0057] S160. Determine the change trend of the influence degree variables of each string according to the chronological order, and determine the corresponding string as the easy-to-clean type or the difficult-to-clean type according to the change trend.

[0058] If the influence degree variable of the same string increases with time, determine the string as the difficult-to-clean type. That is to say, as time goes by, the non-ash fouling area is getting larger and the light transmittance is getting lower, and it is not affected by air drying, moisture and microbial decomposition, which is the difficult-to-clean type, such as bird droppings.

[0059] If the influence degree variable of the same string fluctuates or decreases over time, the string is determined to be easy to clean. That is to say, as time goes by, some non-dust dirt will be decomposed by wind, moisture and microorganisms, so that the area or thickness of non-dust dirt, such as leaves, will decrease.

[0060] It should be noted that if the influence degree variables of the same string are all less than the specified threshold, which is a small value, it is considered that there is no non-dust dirt. For the influence degree variables greater than the specified threshold, the string is determined to be easy to clean or difficult to clean based on its change trend.

[0061] In summary, a string may be dust accumulation type + difficult to clean type, dust accumulation type + easy to clean type, difficult to clean type, easy to clean type or dust accumulation type.

[0062] S170, cleaning the strings according to the dust accumulation type, easy-to-clean type or difficult-to-clean type of the strings.

[0063] If the string is dusty, use clean water to clean the string. Clean water is enough to remove the dust on the surface of the solar panel. If the string is easy to clean, use a scraper and clean water to clean it. For example, first rinse with clean water, then scrape off the dirt with a scraper, and finally rinse with clean water. If the string is difficult to clean, use clean water, detergent and a flexible brush to clean it. For example, mix detergent with clean water and rinse the surface of the solar panel. Use a flexible brush to scrub during the rinsing process to achieve a deep cleaning effect.

[0064] This embodiment does not limit the cleaning method, and the cleaning may be performed by a robot or a cleaning device provided with the solar panel.

[0065] Optionally, after cleaning the strings, the operation of predicting the predicted power generation of each string in each time period is returned to perform the next round of power generation prediction, variable iteration and cleaning operations.

[0066] In the embodiment of the present application, according to the different areas occupied by dirt, the dust accumulation that occupies the entire area of the solar panel is separated, and the non-dust dirt that occupies a part of the area of the solar panel is separated, and a method for predicting power generation is constructed. Then, by predicting the power generation to approach the actual power generation, the dust accumulation transmittance variable and the influence degree variable of the non-dust dirt are iteratively adjusted. In this way, the change trend of the dust accumulation on the solar panel and the change trend of the non-dust dirt can be obtained respectively, so as to determine different types and cleaning methods. When iteratively adjusting the dust accumulation transmittance variable, this embodiment adopts spatial constraint conditions and time constraint conditions, that is, the dust accumulation transmittance variables of different strings are not very different, and the dust accumulation of the same string thickens over time, and the dust accumulation transmittance becomes smaller and smaller. This iterative method is closer to the actual situation, and the change law of the non-dust dirt can also be successfully determined by means of the change law of the dust accumulation.

[0067] The embodiment of the present application provides an electronic device. Refer to Figure 2 , which includes at least one processor 301 and a memory 302 communicatively connected to the at least one processor 301;

[0068] The memory 302 stores instructions executable by the at least one processor 301. The instructions are executed by the at least one processor 301 so that the at least one processor 301 can execute the above-mentioned photovoltaic intelligent cleaning method based on power generation prediction, and thus has at least the same advantages as the above method.

[0069] Optionally, the electronic device further includes an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component is interconnected using different buses and can be mounted on a common motherboard or otherwise as required. The processor can process instructions executed within the electronic device, including instructions for storing graphical information in the memory or on the memory to display a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and multiple memories can be used together, and / or multiple buses and multiple memories can be used together. Similarly, multiple electronic devices (such as a server array, a set of blade servers, or a multi-processor system) can be connected, and each device provides some necessary operations.

[0070] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the photovoltaic intelligent cleaning method based on power generation prediction in the embodiment of the present application. The processor 301 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 301, that is, implements the above-mentioned photovoltaic intelligent cleaning method based on power generation prediction.

[0071] The memory 301 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some instances, the memory 302 may further include a memory remotely provided with respect to the processor, and these remote memories may be connected to the device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0072] The electronic device further includes: an input device 303 and an output device 304. The processor 301, the memory 301, the input device 303, and the output device 304 may be connected through a bus or other means.

[0073] The input device 303 may receive input digital or character information, and the output device 304 may include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), etc. The display device may include but is not limited to a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0074] It should be understood that various forms of the processes shown above may be used, with steps reordered, added, or deleted. For example, the steps described in this application may be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved, and no limitations are imposed herein.

[0075] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims

1. A photovoltaic intelligent cleaning method based on power generation prediction, characterized in that: include: In the target detection area of ​​the solar panel, the predicted power generation of each string in each period is predicted based on the dust transmittance variable, the non-dust dirt influence on light absorption variable, the current environmental characteristics and the parameters of the clean solar panel string; Get the actual power generation of each string in each period; Iterate the dust accumulation transmittance variable and the influence degree variable in each time period to minimize the difference between the predicted power generation and the actual power generation of each string, and obtain the dust accumulation transmittance variable and the influence degree variable in each time period; During the iteration process of the same period, the difference between the dust accumulation transmittance variables of different groups of strings in the same area is less than the set value; during the iteration process of adjacent periods, the dust accumulation transmittance of the same group of strings in the next period is less than the dust accumulation transmittance of the previous period; After completing iterations of multiple time periods, the dust accumulation transmittance variables of the multiple time periods and the influence degree variables of the multiple time periods are summarized; If a set number of dust accumulation transmittance variables among the dust accumulation transmittance variables of multiple time periods are greater than a set threshold, the corresponding string is determined to be a dust accumulation type; Determine the change trend of the influence degree variable of each string according to the chronological order, and determine whether the corresponding string is an easy-to-clean type or a difficult-to-clean type according to the change trend; Clean the strings according to the dust accumulation type, easy-to-clean type or difficult-to-clean type of the strings.

2. The method according to claim 1, characterized in that: Based on the dust transmittance variable, the non-dust dirt influence on light absorption variable, the current environmental characteristics and the parameters of the clean solar panel string, the predicted power generation of each string in each period is predicted, including: The predicted power generation P of each string in each period is calculated according to the following formula: Among them, G is the light intensity, A is the area of ​​the solar panel string, η is the photoelectric conversion efficiency, ranging from 0 to 1; t is the duration of the time period, R is the original reflectivity of the solar panel surface, ranging from 0 to 1; σ is the dust transmittance variable, ranging from 0 to 1; τ is the dust area ratio, which is a fixed value of 1; δ is the variable of the degree of influence of non-dust dirt on light absorption, which represents the result of adding the reciprocal of the transmittance of each non-dust dirt multiplied by the area ratio.

3. The method according to claim 2, characterized in that Determine the change trend of the influence degree variable of each string according to the time sequence, and determine whether the corresponding string is an easy-to-clean type or a difficult-to-clean type according to the change trend, including: If the influence degree variable of the same string increases over time, the string is determined to be a difficult-to-clean type; If the influence degree variable of the same string fluctuates up and down or decreases over time, the string is determined to be an easy-to-clean type.

4. The method according to claim 3, characterized in that Clean the strings according to the type of dust accumulation, easy-to-clean type or difficult-to-clean type of the strings, including: If the string is dusty, clean it with clean water; If the string is of the easy-to-clean type, use a scraper and clean water to clean it; If the string is difficult to clean, use clean water, detergent and a soft brush to clean it.

5. The method according to claim 4, characterized in that After cleaning the strings, the method further includes: returning to predict the predicted power generation of each string in each time period.

6. An electronic device, characterized in that: include: at least one processor, and a memory communicatively coupled to at least one of the processors; The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the photovoltaic intelligent cleaning method based on power generation prediction as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that: The medium stores computer instructions, and the computer instructions are used to enable the computer to execute the photovoltaic intelligent cleaning method based on power generation prediction according to any one of claims 1-5.

Images