Photovoltaic system maintenance method, device, equipment and storage medium

Abstract

This application relates to a photovoltaic system maintenance method, apparatus, device, and storage medium. This method involves obtaining solar radiation intensity during a first time period; obtaining a predicted photovoltaic system power generation during a second time period based on the solar radiation intensity during the first time period and a pre-trained prediction model; obtaining the actual photovoltaic system power generation during the second time period; and performing maintenance on the photovoltaic system based on the predicted power generation during the second time period and the actual power generation during the second time period. This application addresses the technical problem of determining whether a photovoltaic system requires maintenance based on solar radiation intensity.

Description

Technical Field

[0001] The present application relates to the field of solar power generation, and in particular to a maintenance method, device, equipment and storage medium for a photovoltaic system. Background Art

[0002] In recent years, solar energy has attracted considerable attention as a renewable, clean energy source. Photovoltaic panels, by converting sunlight into electricity, help reduce carbon dioxide emissions from power plants, contributing to improved air quality and reduced carbon emissions.

[0003] Photovoltaic power generation efficiency reflects the actual power generation efficiency of a photovoltaic system and has a significant impact on the system's power output. However, the efficiency of a photovoltaic system is affected by many factors, such as weather and dust coverage. Excessive dust coverage of a photovoltaic system can cause a hot spot effect, reducing the system's power generation and shortening the lifespan of its components.

[0004] Existing technologies can predict the maintenance cycle for photovoltaic systems under consistent meteorological conditions. However, in practice, varying meteorological conditions directly affect the intensity of solar radiation, which significantly impacts the power generation of photovoltaic systems. Therefore, existing technologies are unable to calculate the impact of dust on power generation, taking into account the varying solar radiation intensity caused by varying meteorological conditions. Consequently, in practice, it is impossible to determine the need for maintenance on photovoltaic systems when dust levels significantly impact power generation. Summary of the Invention

[0005] The present application provides a maintenance method, device, equipment and storage medium for a photovoltaic system, which are used to solve the technical problem of determining whether maintenance of the photovoltaic system is required based on the factor of solar radiation intensity.

[0006] In a first aspect, an embodiment of the present application provides a method for maintaining a photovoltaic system, comprising:

[0007] Obtain solar radiation intensity during the first time period;

[0008] Obtaining a predicted power generation of the photovoltaic system in a second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model;

[0009] Obtaining the actual power generation of the photovoltaic system in the second time period;

[0010] The photovoltaic system is maintained based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period.

[0011] Optionally, obtaining the predicted power generation of the photovoltaic system in the second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model includes:

[0012] The predicted solar radiation intensity for the second time period is calculated based on the solar radiation intensity for the first time period and a pre-trained prediction model;

[0013] Obtaining a difference between the predicted solar radiation intensity during the second time period and the solar radiation intensity during the first time period;

[0014] Based on the difference, a predicted power generation of the photovoltaic system in the second time period is obtained.

[0015] Optionally, obtaining the predicted photovoltaic system power generation in the second time period based on the difference includes:

[0016] When the difference between the solar radiation intensity predicted in the second time period and the solar radiation intensity in the first time period is greater than a first threshold, calculating the predicted power generation of the photovoltaic system in the second time period according to the reference power generation corresponding to the photovoltaic system;

[0017] or,

[0018] When the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period is less than or equal to a first threshold, the actual power generation of the photovoltaic system in the first time period is obtained, and the actual power generation of the photovoltaic system in the first time period is used as the predicted power generation of the photovoltaic system in the second time period.

[0019] Optionally, the process of obtaining the reference power generation corresponding to the photovoltaic system includes:

[0020] Selecting some photovoltaic panels from the photovoltaic system as basic photovoltaic panels; cleaning the basic photovoltaic panels; obtaining actual power generation of the basic photovoltaic panels in a second time period; and using the actual power generation of the basic photovoltaic panels in the second time period as a reference power generation;

[0021] or,

[0022] When the actual solar radiation intensity in the historical time period is the same as the actual solar radiation intensity in the second time period, the actual power generation of the photovoltaic system in the historical time period is recorded; the actual power generation of the photovoltaic system in the historical time period is used as the reference power generation, and the historical time period is the time period before the first time period.

[0023] Optionally, the maintaining the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period includes:

[0024] Calculating the difference between the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period;

[0025] When the difference is greater than or equal to a second threshold, maintenance information is sent to the designated terminal.

[0026] Optionally, when the difference is greater than or equal to a second threshold, sending maintenance information to a designated terminal includes:

[0027] When the difference is greater than or equal to a second threshold, the number of statistics is increased by one;

[0028] When the statistical number is less than a preset third threshold, maintenance information is sent to the designated terminal to remind the user that the actual power generation of the photovoltaic panel in the second time period is abnormal, or, when the statistical number is greater than or equal to the third threshold, maintenance information is sent to the designated terminal to notify the user that the photovoltaic system needs to be cleaned.

[0029] Optionally, before obtaining the actual power generation of the photovoltaic system in the first time period and the solar radiation intensity in the first time period, the method further includes:

[0030] Obtain solar radiation intensity data for training;

[0031] Establishing the prediction model based on a predetermined prediction algorithm;

[0032] Dividing the training solar radiation intensity data into a training set and a test set;

[0033] Training the prediction model using the training set;

[0034] Using the test set to evaluate the results output by the prediction model;

[0035] When the result of evaluating the output of the prediction model meets the preset termination condition, the training is stopped to obtain the trained prediction model.

[0036] In a second aspect, an embodiment of the present application provides a maintenance device for a photovoltaic system, comprising:

[0037] A first acquiring unit, configured to acquire solar radiation intensity during a first time period;

[0038] A prediction unit, configured to obtain a predicted power generation of the photovoltaic system in a second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model;

[0039] A second acquiring unit is used to acquire the actual power generation of the photovoltaic system in a second time period;

[0040] A maintenance unit is configured to maintain the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period.

[0041] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and a communication bus, wherein the processor and the memory communicate with each other via the communication bus;

[0042] The memory is used to store computer programs;

[0043] The processor is used to execute the program stored in the memory to implement the photovoltaic system maintenance method described in the first aspect.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, characterized in that when the computer program is executed by a processor, the photovoltaic system maintenance method described in the first aspect is implemented.

[0045] The above-mentioned technical solution provided by the embodiment of the present application has the following advantages compared with the existing technology: the method provided by the embodiment of the present application obtains the solar radiation intensity in the first time period; obtains the predicted power generation of the photovoltaic system in the second time period based on the solar radiation intensity in the first time period and the pre-trained prediction model; obtains the actual power generation of the photovoltaic system in the second time period; and maintains the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period, which can more accurately guide when to clean the photovoltaic system and reduce waste and economic losses in the maintenance of the photovoltaic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 This is a flow chart of a method for maintaining a photovoltaic system according to an embodiment of the present application;

[0049] Figure 2 Schematic diagram of the process of establishing a prediction model in the embodiment of the present application;

[0050] Figure 3 This is a flow chart of a specific implementation of the photovoltaic system maintenance method according to an embodiment of the present application;

[0051] Figure 4 This is a schematic structural diagram of a maintenance device for a photovoltaic system according to an embodiment of the present application;

[0052] Figure 5 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0053] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0055] The present application provides a method for maintaining a photovoltaic system. Figure 1 As shown, the method may include the following steps:

[0056] Step 101: Obtain solar radiation intensity in a first time period.

[0057] It should be understood that in this application, the first time period and the second time period are two consecutive time periods. The first time period and the second time period are of the same length. The first time period and the second time period described below can be set according to actual needs of the application. For example, the first time period and the second time period are both set to 24 hours.

[0058] In an exemplary embodiment, before obtaining the solar radiation intensity in the first time period, it also includes: obtaining training solar radiation intensity data; establishing a prediction model based on a predetermined prediction algorithm; dividing the training solar radiation intensity data into a training set and a test set; using the training set to train the prediction model; using the test set to evaluate the results output by the prediction model; when the result of evaluating the results output by the prediction model meets the preset termination condition, stopping the training to obtain the trained prediction model.

[0059] It should be understood that in this method, it is necessary to predict the solar radiation intensity for the second time period based on the solar radiation intensity for the first time period. To this end, this embodiment provides a method for establishing a prediction model for predicting the solar radiation intensity for the second time period before obtaining the actual power generation of the photovoltaic system and the solar radiation intensity for the first time period.

[0060] In an example, the method for establishing a prediction model requires that the training solar radiation intensity data obtained is the solar radiation intensity data obtained within one consecutive year. The prediction algorithm used can be a time series algorithm. After obtaining the training solar radiation intensity data, the data can also be preprocessed and analyzed. The preprocessing includes processing dirty data (such as data specification conversion, etc.), and the periodicity of the solar radiation intensity can also be analyzed. The daily cycle is 24 hours. Then, the training solar radiation intensity data is used to train the model. Specifically, the training solar radiation intensity data is divided into a training set and a test set, wherein the training set is used to train the model and the test set is used to evaluate the model results. Evaluate whether the optimization training results meet the termination conditions. If so, you can start using the prediction model to predict the solar radiation intensity of the next cycle.

[0061] Step 102: Based on the solar radiation intensity in the first time period and a pre-trained prediction model, obtain the predicted power generation of the photovoltaic system in the second time period;

[0062] In an exemplary embodiment, based on the solar radiation intensity in the first time period and a pre-trained prediction model, the predicted power generation of the photovoltaic system in the second time period is obtained, including: calculating the predicted solar radiation intensity in the second time period based on the solar radiation intensity in the first time period and the pre-trained prediction model; obtaining the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period; and obtaining the predicted power generation of the photovoltaic system in the second time period based on the difference.

[0063] It should be understood that this embodiment provides a specific implementation method for obtaining the predicted power generation of the photovoltaic system for a second time period. In this method, the predicted solar radiation intensity for the second time period is first obtained based on the solar radiation intensity for the first time period and a pre-trained prediction model. Then, the difference between the predicted solar radiation intensity for the second time period and the solar radiation intensity for the first time period is calculated, and the predicted power generation of the photovoltaic system for the second time period is obtained based on this difference.

[0064] In an exemplary embodiment, based on the difference, the predicted power generation of the photovoltaic system in the second time period is obtained, including: when the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period is greater than a first threshold, the predicted power generation of the photovoltaic system in the second time period is calculated according to the reference power generation corresponding to the photovoltaic system; or, when the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period is less than or equal to the first threshold, the actual power generation of the photovoltaic system in the first time period is obtained, and the actual power generation of the photovoltaic system in the first time period is used as the predicted power generation of the photovoltaic system in the second time period.

[0065] In this application, the method for obtaining the actual power generation of the photovoltaic system in a certain time period can be to directly count the total power output of the photovoltaic system during the time period, which can more accurately calculate the actual power generation of the photovoltaic system. Alternatively, the power generation output of a portion of the photovoltaic panels in the photovoltaic system during the time period can be counted, and the actual power generation of the photovoltaic system can be calculated based on the ratio of the area of the portion of the photovoltaic panels to the area of the photovoltaic system.

[0066] It should be understood that this embodiment further provides a specific implementation method for the step described above of obtaining a predicted photovoltaic system power generation for the second time period based on the difference. Based on the calculated difference between the predicted solar radiation intensity for the second time period and the solar radiation intensity for the first time period, this difference is compared with a preset first threshold. When this difference is greater than the first threshold, it is considered that the difference in solar radiation intensity between the two time periods is too large, and the actual power generation of the photovoltaic system in the previous time period is not meaningful as a reference. The predicted power generation is calculated using the preset reference power generation. When this difference is less than the first threshold, it is considered that the solar radiation intensity for the two time periods is substantially the same, and the actual power generation of the photovoltaic system in the previous time period can be directly used as the predicted power generation for the next time period.

[0067] In an exemplary embodiment, the process of obtaining the reference power generation corresponding to the photovoltaic system includes: selecting some photovoltaic panels from the photovoltaic system as basic photovoltaic panels; cleaning the basic photovoltaic panels; obtaining the actual power generation of the basic photovoltaic panels in the second time period; using the actual power generation of the basic photovoltaic panels in the second time period as the reference power generation; or, when the actual solar radiation intensity in the historical time period is the same as the actual solar radiation intensity in the second time period, recording the actual power generation of the photovoltaic system in the historical time period; using the actual power generation of the photovoltaic system in the historical time period as the reference power generation, where the historical time period is the time period before the first time period.

[0068] It should be understood that this embodiment specifically provides two methods for obtaining the reference power generation required for the above calculation.

[0069] Method 1:

[0070] A portion of photovoltaic panels is selected from the photovoltaic system as base photovoltaic panels. At the beginning of the second time period, the base photovoltaic panels are cleaned to ensure that the actual power generation of the base photovoltaic panels, used as a reference, is not affected by dust. The actual power generation of the base photovoltaic panels during the entire second time period is calculated and used as the reference power generation. When using this method, the predicted power generation of the photovoltaic system can be calculated by using the ratio of the area of the base photovoltaic panels to the area of the entire photovoltaic system to determine the power generation of the entire photovoltaic system without dust, i.e., the predicted power generation of the photovoltaic system in the second event period.

[0071] Method 2:

[0072] This method proposes recording the actual power generation of the PV system under various solar radiation intensities and when dust-free, over a certain historical period, prior to executing the PV system maintenance method provided herein. To account for factors such as aging of the PV panels, the recording can be set to be repeated at regular intervals to update the actual power generation data of the PV system, for example, annually.

[0073] In actual use, the specific value of the predicted solar radiation intensity for the second time period obtained above is retrieved in the record. When the value of the actual solar radiation intensity for a certain historical time period is equal to the value of the predicted solar radiation intensity for the second time period, the actual power generation of the photovoltaic system in the historical time period corresponding to the actual solar radiation intensity of the historical time period in the record is used as the reference power generation.

[0074] It should also be noted that while Method 2 above uses a photovoltaic system, in practice, the same effect can be achieved using a reference photovoltaic panel with a preset area. This requires only an additional conversion step, calculating the ratio of the reference photovoltaic panel area to the photovoltaic system area. When recording the actual power generation of the reference photovoltaic panel, the preset area can be set according to actual needs, such as setting a reference photovoltaic panel per unit area to facilitate conversion.

[0075] Step 103: Obtain the actual power generation of the photovoltaic system in the second time period.

[0076] Step 104 : Perform maintenance on the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period.

[0077] In an exemplary embodiment, when the difference is greater than or equal to a second threshold, maintenance information is sent to a designated terminal, including: calculating the difference between the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period; when the difference is greater than or equal to the second threshold, maintenance information is sent to the designated terminal.

[0078] It should be understood that the predicted power generation of the photovoltaic system during the second time period obtained above represents the power generation that the photovoltaic system would have generated if there were no dust impact. If the difference between this and the actual power generation of the photovoltaic system during the second time period exceeds a second threshold set according to actual needs, it is considered that dust has significantly impacted the power generation of the photovoltaic system. A maintenance message is sent to the designated terminal to notify of this situation.

[0079] In an exemplary embodiment, when the difference is greater than or equal to the second threshold, maintenance information is sent to the designated terminal, including: when the difference is greater than or equal to the second threshold, the statistical number is increased by one; when the statistical number is less than a preset third threshold, maintenance information is sent to the designated terminal to remind the user that the actual power generation of the photovoltaic panel in the second time period is abnormal, or, when the statistical number is greater than or equal to the third threshold, maintenance information is sent to the designated terminal to notify the user that the photovoltaic system needs to be cleaned.

[0080] It should be understood that, in practical applications, weather conditions are influenced by a variety of factors and exhibit a certain degree of randomness. For example, while current weather forecasting methods have become increasingly sophisticated, weather forecast results still occasionally contain errors. Similarly, the solar radiation results obtained through the prediction model in this application may also occasionally be inaccurate.

[0081] Taking the above problems into consideration, the process of sending maintenance information is set to design a statistical number, and each time the difference is greater than or equal to the second threshold, the number is increased by one. When the number is greater than or equal to the preset third threshold, it is considered that the dust has a significant impact on the power generation of the photovoltaic system, and the user is notified that the photovoltaic system needs to be cleaned. When the number is less than the third threshold, considering that there may be an accidental error in the prediction of solar radiation intensity, the user will only be informed of the abnormal actual power generation of the photovoltaic panel in the second time period, and the user will not be notified to clean the photovoltaic system. For example, the first time period and the second time period are set to 1 day, and the third threshold is set to 10 times. That is, when the actual power generation of the photovoltaic panel is abnormal for 10 days, the user will be notified to clean the photovoltaic system.

[0082] The above steps 101 to 104 are described below with reference to a specific embodiment:

[0083] In this specific embodiment, the first time period and the second time period are set to have a duration of one day.

[0084] First, establish a prediction model. The prediction model established in this specific embodiment is a time series model. Specifically, the ARMA algorithm is used to study the time series. The ARMA algorithm is composed of an autoregressive model (AR model) and a moving average model (MA model). The characteristic of this algorithm is that it can only perform short-term predictions (usually in hours). As time goes by, new observations need to be added to correct the prediction results. The specific steps for establishing a prediction model are as follows:

[0085] Step 201: Obtain solar radiation intensity data for a whole year, with a data collection frequency of once per hour.

[0086] Step 202: pre-process and analyze the data. The pre-processing includes processing dirty data (such as data format conversion, etc.), and observes that the solar radiation intensity is periodic, with a daily cycle of 24 hours.

[0087] Step 203: Establish a time series model.

[0088] Step 204: Use the training data to train the model. Specifically, the data from step 1 is divided into a training set and a test set, where the training set is used to train the model and the test set is used to evaluate the model results. Use the training data to train the time series model.

[0089] Step 205: Evaluate whether the optimization training result meets the termination condition. If so, the prediction model is established; if not, return to step 203 to re-establish the time series model.

[0090] Once the prediction model is established, the trained time series model can be used to predict the solar radiation intensity for the next period. The prediction is performed in hourly units, meaning the solar radiation intensity at times t+1, t+2, t+3, and so on, is predicted for t+24, where t is the starting time. Finally, the predicted solar radiation intensity is obtained by summing the results of each prediction.

[0091] It should be noted that the time series model trained using the ARMA algorithm can only be used for short-term predictions. Therefore, the hourly solar radiation intensity of the first day can be obtained at the second day (for example, at 0:00 on the second day) by obtaining it from the Internet. Similarly, the trained time series model can be used on the previous day to predict the solar radiation intensity value of the second day. The same method can be used on the second day to predict the solar radiation intensity value of the third day, so that this method can be repeated.

[0092] Second, a maintenance method of a photovoltaic system. In this specific embodiment, the photovoltaic system refers to a photovoltaic system installed in a home, including multiple photovoltaic panels of the same specifications.

[0093] Let the area of a single complete photovoltaic panel be x and the total area of the photovoltaic system be X.

[0094] In practical applications, photovoltaic system power generation is related to weather conditions. To understand the impact of dust accumulation on photovoltaic system power generation, it is necessary to exclude the influence of weather conditions. Considering that various weather factors are directly reflected in the daily solar radiation intensity data, which significantly affects photovoltaic system power generation, solar radiation intensity is used as the specific parameter for weather factors affecting photovoltaic system power generation.

[0095] A complete photovoltaic panel (equipped with a cleaning device) in the photovoltaic system is selected as base photovoltaic panel A to obtain the power generation of the photovoltaic system in a dust-free state. The impact of dust on the power generation of the photovoltaic system is compared with the power generation of the photovoltaic system in the actual application environment. A cleaning device is installed on base photovoltaic panel A to control its cleaning of base photovoltaic panel A. When base photovoltaic panel A needs to be cleaned, the cleaning time is set at 8:00 am and the power generation statistics time is set at 10:00 pm. This time can be adjusted according to different regions. It is mainly set according to the solar radiation intensity in the region. For example, in Xinjiang, my country, the sun rises around 6:00 am and sets at 10:00 pm in summer. Therefore, the cleaning time can be set at around 5:00 am and the power generation statistics time can be set at around 11:00 pm.

[0096] The following are the specific implementation steps of the photovoltaic system maintenance method in this embodiment:

[0097] Step 301: The basic photovoltaic panel power generation on the first day is obtained as P, and the actual power generation of the photovoltaic system on the first day is P*X / x;

[0098] Step 302: At 10 pm, use the time series model to predict the solar radiation intensity value of the next day;

[0099] Step 303: Obtain the absolute value of the difference between the solar radiation intensity value on the second day and the solar radiation value on the first day, and determine whether it is within the specified threshold value Y (if so, it is assumed that the meteorological conditions at the next moment are the same as those on the current day, and the difference between the power generation of the photovoltaic system on the second day and the power generation of the photovoltaic system on the first day is only affected by dust). If so and the user has not given any instructions, proceed to step 304. If not, or if the user manually selects to use basic photovoltaic panel A for judgment, proceed to step 306 (at this time, it is assumed that the meteorological conditions on the second day are different from those on the first day, and the power generation of the photovoltaic system on the second day is compared with the power generation of the photovoltaic system on the first day, and is affected by both meteorological conditions and dust).

[0100] Step 304: Set the predicted power generation of the photovoltaic system on the second day to the power generation of the photovoltaic system on the first day;

[0101] Step 305: Obtain the actual power generation Pi of the photovoltaic system on the next day; calculate the cumulative power generation affected by dust as |P*X / x-Pi|, and go to step 308;

[0102] Step 306: Clean the basic photovoltaic panel A at 8:00 am the next day;

[0103] Step 307: At 10 pm on the second day, the actual power generation Pi of the photovoltaic system on the second day and the predicted power generation of the photovoltaic system on the second day are obtained as P~*X / x, where P~ is the power generation of the basic photovoltaic panel A; the cumulative power generation affected by dust is |P~*X / x-Pi|;

[0104] Step 308: Determine whether the dust power generation loss exceeds a threshold. If so, go to step 309; otherwise, return to step 302 and start a new round of prediction.

[0105] Step 309: Accumulate the number of days with abnormal power generation.

[0106] Step 310: The server determines whether the number of days with abnormal power generation is predicted to exceed a threshold. If so, the server proceeds to step 311; otherwise, the server proceeds to step 312.

[0107] Step 311: The server notifies the user to perform a cleaning operation.

[0108] Step 312: The server reminds the user that the power generation of the photovoltaic panel system today is abnormal, and there may be a lot of dust.

[0109] Based on the same concept, a maintenance device for a photovoltaic system is provided in the embodiment of the present application. The specific implementation of the device can be found in the description of the method embodiment part, and the repeated parts will not be repeated. Figure 4 As shown, the device mainly includes:

[0110] A first acquiring unit 401 is configured to acquire solar radiation intensity during a first time period;

[0111] The prediction unit 402 is configured to obtain a predicted power generation of the photovoltaic system in a second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model;

[0112] The second acquiring unit 403 is configured to acquire the actual power generation of the photovoltaic system during the second time period;

[0113] The maintenance unit 404 is configured to perform maintenance on the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period.

[0114] Based on the same concept, an electronic device is also provided in the embodiment of the present application, such as Figure 5As shown, the electronic device mainly includes: a processor 501, a memory 502 and a communication bus 503, wherein the processor 501 and the memory 502 communicate with each other via the communication bus 503. The memory 502 stores a program that can be executed by the processor 501, and the processor 501 executes the program stored in the memory 502 to implement the following steps:

[0115] Obtain solar radiation intensity during the first time period;

[0116] Based on the solar radiation intensity in the first time period and a pre-trained prediction model, obtaining the predicted power generation of the photovoltaic system in the second time period;

[0117] Obtaining the actual power generation of the photovoltaic system in the second time period;

[0118] The photovoltaic system is maintained based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period.

[0119] The communication bus 503 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 503 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0120] The memory 502 may include a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor 501.

[0121] The above-mentioned processor 501 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc., and can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0122] In another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is run on a computer, the computer executes the photovoltaic system maintenance method described in the above embodiment.

[0123] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions are transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape, etc.), an optical medium (e.g., a DVD) or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0124] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0125] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is intended to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for maintaining a photovoltaic system, characterized in that: include: Obtain solar radiation intensity during the first time period; Obtaining a predicted power generation of the photovoltaic system in a second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model; Obtaining the actual power generation of the photovoltaic system in the second time period; performing maintenance on the photovoltaic system based on the predicted power generation of the photovoltaic system during the second time period and the actual power generation of the photovoltaic system during the second time period; The obtaining of the predicted power generation of the photovoltaic system in the second time period includes: when the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period is greater than a first threshold, calculating the predicted power generation of the photovoltaic system in the second time period according to the reference power generation corresponding to the photovoltaic system; The process of obtaining the reference power generation corresponding to the photovoltaic system includes: selecting some photovoltaic panels from the photovoltaic system as basic photovoltaic panels; cleaning the basic photovoltaic panels; obtaining the actual power generation of the basic photovoltaic panels in a second time period; and using the actual power generation of the basic photovoltaic panels in the second time period as the reference power generation.

2. The method according to claim 1, characterized in that The step of obtaining the predicted power generation of the photovoltaic system in the second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model includes: The predicted solar radiation intensity for the second time period is calculated based on the solar radiation intensity for the first time period and a pre-trained prediction model; Obtaining a difference between the predicted solar radiation intensity during the second time period and the solar radiation intensity during the first time period; Based on the difference, a predicted power generation of the photovoltaic system in the second time period is obtained.

3. The method according to claim 2, characterized in that The step of obtaining the predicted photovoltaic system power generation in the second time period based on the difference further includes: When the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period is less than or equal to a first threshold, the actual power generation of the photovoltaic system in the first time period is obtained, and the actual power generation of the photovoltaic system in the first time period is used as the predicted power generation of the photovoltaic system in the second time period.

4. The method according to claim 1, wherein The maintaining of the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period includes: Calculating the difference between the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period; When the difference is greater than or equal to a second threshold, maintenance information is sent to the designated terminal.

5. The method according to claim 4, characterized in that When the difference is greater than or equal to a second threshold, sending maintenance information to a designated terminal includes: When the difference is greater than or equal to the second threshold, the number of statistics is increased by one; When the statistical number is less than a preset third threshold, maintenance information is sent to the designated terminal to remind the user that the actual power generation of the photovoltaic panel in the second time period is abnormal, or, when the statistical number is greater than or equal to the third threshold, maintenance information is sent to the designated terminal to notify the user that the photovoltaic system needs to be cleaned.

6. The method according to claim 1, characterized in that Before obtaining the solar radiation intensity in the first time period, the method further includes: Obtain solar radiation intensity data for training; Establishing the prediction model based on a predetermined prediction algorithm; Dividing the training solar radiation intensity data into a training set and a test set; Training the prediction model using the training set; Using the test set to evaluate the results output by the prediction model; When the result of evaluating the output of the prediction model meets the preset termination condition, the training is stopped to obtain the trained prediction model.

7. A maintenance device for a photovoltaic system, characterized in that: include: A first acquiring unit, configured to acquire solar radiation intensity during a first time period; A prediction unit, configured to obtain a predicted power generation of the photovoltaic system in a second time period based on the solar radiation intensity in the first time period and a pre-trained prediction model; A second acquiring unit is used to acquire the actual power generation of the photovoltaic system in a second time period; a maintenance unit, configured to maintain the photovoltaic system based on the predicted power generation of the photovoltaic system in the second time period and the actual power generation of the photovoltaic system in the second time period; The prediction unit is specifically configured to: when the difference between the predicted solar radiation intensity in the second time period and the solar radiation intensity in the first time period is greater than a first threshold, calculate the predicted power generation of the photovoltaic system in the second time period according to the reference power generation corresponding to the photovoltaic system; The prediction unit is further used to: select some photovoltaic panels from the photovoltaic system as basic photovoltaic panels; clean the basic photovoltaic panels; obtain the actual power generation of the basic photovoltaic panels in the second time period; and use the actual power generation of the basic photovoltaic panels in the second time period as a reference power generation.

8. An electronic device, characterized in that: include: A processor, a memory, and a communication bus, wherein the processor and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to execute the program stored in the memory to implement the photovoltaic system maintenance method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the photovoltaic system maintenance method according to any one of claims 1 to 6 is implemented.

Images