Photovoltaic module cleaning method and system based on multi-cycle meteorological prediction

Abstract

The invention relates to the technical field of photovoltaic power generation operation and maintenance, and discloses a photovoltaic module cleaning method and system based on multi-cycle meteorological prediction. According to the method and the system, medium-and-long-term weather prediction data is utilized, conversion of cleaning decision from'passive response 'to'active optimization' is realized, an optimal cleaning window can be planned in advance, and power generation benefits are maximized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of photovoltaic power generation operation and maintenance, in particular to a photovoltaic module cleaning method and system based on multi-period meteorological prediction. BACKGROUND

[0002] As an important part of clean energy, the power generation efficiency of photovoltaic power generation is easily affected by the pollution (dust, snow, etc.) on the surface of the module. At present, the cleaning and maintenance of photovoltaic power stations mainly relies on fixed-period cleaning or after-response cleaning. Fixed-period cleaning (such as once a month) lacks adaptability to actual meteorological conditions, which may lead to over-cleaning during frequent rainfall periods, resulting in waste of water resources and labor costs, and even cleaning during non-profit periods, resulting in a negative return on investment. After-response cleaning (such as cleaning after monitoring power attenuation) has a lag and cannot prevent power generation loss.

[0003] In the prior art, although some schemes introduce short-term weather forecasts (such as 1-3 days in the future) to avoid rainfall immediately after cleaning, the prediction period is too short to support optimal operation and maintenance decisions in the medium and long term. In addition, existing methods generally lack accurate quantitative models of the dynamic economic relationship between "cleaning cost" and "cleaning benefit", making it difficult to find the best cleaning opportunity to maximize economic benefits throughout the life cycle.

[0004] Therefore, there is an urgent need in the art for an intelligent method and system that can integrate medium and long-term meteorological prediction information, dynamically evaluate and optimize cleaning decisions, and thus maximize the operation and maintenance benefits of photovoltaic power stations. SUMMARY

[0005] The present application aims to overcome the shortcomings of the prior art and provide a photovoltaic module cleaning method and system based on multi-period meteorological prediction, which is characterized by changing the cleaning decision from an experience-based task to a data model-based decision.

[0006] To achieve the above-mentioned purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides a photovoltaic module cleaning method based on multi-period meteorological prediction, comprising the following steps: Obtaining physical parameters, historical operation data of a target photovoltaic power station, and high-precision meteorological prediction data for a future preset period; the physical parameters are used to construct a physical basis model of the power station; Based on the physical basis model and the meteorological prediction data, simulating and calculating a first theoretical power generation sequence under the scenario of no cleaning in the preset period; Taking multiple time points in the preset period as candidate cleaning time points, for each candidate cleaning time point, simulating and calculating a second theoretical power generation sequence from the time point of performing cleaning until the end of the preset period; Based on the first theoretical power generation sequence and each of the second theoretical power generation sequences, an expected additional power generation benefit corresponding to each candidate cleaning time point is calculated in combination with the on-grid electricity price; Based on a preset cleaning cost model and the expected additional power generation benefit, an expected return on investment (ROI) corresponding to each candidate cleaning time point is calculated; From all the candidate cleaning time points, a time point that meets a preset constraint condition and has the highest expected ROI is selected as an optimal cleaning time point, and a cleaning decision instruction is generated; the preset constraint condition at least includes a meteorological constraint.

[0007] Preferably, the future preset period of the high-precision meteorological prediction data is not less than 7 days, and includes global horizontal irradiance (GHI), direct normal irradiance (DNI), ambient temperature, precipitation, and atmospheric pollutant concentration data.

[0008] Preferably, the simulation calculation is performed by the following way: Using the physical basis model, the basis power generation power under the ideal clean state is calculated according to the meteorological prediction data; The basis power generation power is corrected by introducing a dust loss coefficient model to simulate the power generation loss caused by pollution; wherein the dust loss coefficient is reset at the corresponding candidate cleaning time point.

[0009] Preferably, the dust loss coefficient model is a prediction model dynamically updated based on historical non-rainy days, wind speed, and atmospheric pollutant concentration data.

[0010] Preferably, the preset constraint condition includes a meteorological constraint, which requires that there is no precipitation or the precipitation is below a threshold value on the candidate cleaning time point and in the subsequent preset time.

[0011] In a second aspect, the application also provides a multi-period meteorological prediction-based photovoltaic module cleaning system, comprising: A data acquisition module is configured to acquire physical parameters of a target photovoltaic power station, historical operation data, and high-precision meteorological prediction data for a future preset period; wherein the physical parameters are used to construct a physical basis model of the power station; Preferably, the future preset period of the high-precision meteorological prediction data is not less than 7 days, and includes global horizontal irradiance (GHI), direct normal irradiance (DNI), ambient temperature, precipitation, and atmospheric pollutant concentration data; A first simulation calculation module is configured to simulate a first theoretical power generation sequence under a non-cleaning scenario in a preset period based on the obtained physical basis model and meteorological prediction data; Preferably, the first simulation calculation module performs simulation calculation by the following way: The physical basic model is used to calculate the basic power generation in an ideal clean state according to meteorological prediction data; and a dust loss coefficient model is introduced to correct the basic power generation, so as to simulate the power generation loss caused by pollution; wherein, the dust loss coefficient model is a prediction model dynamically updated based on historical number of days without precipitation, wind speed and atmospheric pollutant concentration data. The second simulation calculation module is configured to simulate a second theoretical power generation sequence from the candidate cleaning time point to the end of the preset period after cleaning at the candidate cleaning time point. The second simulation calculation module simulates in the following manner: The physical basic model is used to calculate the basic power generation in an ideal clean state according to meteorological prediction data; and a dust loss coefficient model is introduced to correct the basic power generation, so as to simulate the power generation loss caused by pollution; wherein, the dust loss coefficient is reset at the candidate cleaning time point; wherein, the dust loss coefficient model is a prediction model dynamically updated based on historical number of days without precipitation, wind speed and atmospheric pollutant concentration data. The power generation income calculation module is configured to calculate expected additional power generation income corresponding to each candidate cleaning time point based on the first theoretical power generation sequence and each second theoretical power generation sequence, and in combination with the on-grid electricity price. The investment return rate calculation unit is configured to calculate expected investment return rates corresponding to each candidate cleaning time point based on a preset cleaning cost model and the expected additional power generation income; and the instruction generation module is configured to select a time point that meets a preset constraint condition and has the highest expected investment return rate from all candidate cleaning time points as an optimal cleaning time point, and generate a cleaning decision instruction; wherein, the preset constraint condition at least includes a meteorological constraint; wherein, the meteorological constraint includes that there is no precipitation or the precipitation is lower than a threshold value on the candidate cleaning time point and in the subsequent preset number of days.

[0012] Preferably, the system further comprises a physical basic model construction module configured to construct and maintain the physical basic model according to the physical parameters.

[0013] In a third aspect, the present application further provides a computer device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method of the first aspect when executing the program.

[0014] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program executable by a processor to implement the method of the first aspect.

[0015] In a fifth aspect, the present application also provides a computer program product carrying program codes, the program codes comprising instructions for executing the method according to the first aspect.

[0016] The effects of the computer device, the computer readable storage medium and the computer program product are described above in the description of the method, and will not be repeated here.

[0017] Compared with the prior art, the present application has the following advantages: 1. Proactive and initiative: By using medium and long term weather forecast data, the cleaning decision has changed from "passive response" to "active optimization", which can plan the best cleaning window in advance and maximize the power generation benefit; 2. Quantitative decision and maximum economic benefit: By constructing a refined power generation prediction model and a cost model, the cleaning decision is quantified as a return on investment (ROI) comparison problem, ensuring that each cleaning action has clear economic benefits and avoiding ineffective cleaning; 3. Strong adaptability: The dust loss coefficient model can dynamically update combined with local environmental factors (such as wind speed and pollution), making the power generation prediction more realistic and improving the applicability and accuracy of the system under different geographical and environmental conditions; 4. Optimal allocation of resources: By introducing weather and resource constraints, cleaning in adverse weather or when resources are not available is avoided, effectively saving water resources, manpower and equipment costs, and achieving precise investment of operation and maintenance resources.

[0018] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments, the drawings herein are incorporated into the specification and form a part of the specification, which show the embodiments consistent with the present disclosure, and are used to illustrate the technical solutions of the present disclosure together with the specification. It should be understood that the following drawings only show some embodiments of the present disclosure, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings: Figure 1 is a step flow chart of the photovoltaic module cleaning method in the embodiments of the present application; Figure 2 is a structural schematic diagram of the photovoltaic module cleaning system in the embodiments of the present application; Figure 3 is a specific implementation diagram of the photovoltaic module cleaning method in the embodiments of the present application; Figure 4 This is a schematic diagram of the structure of the computer device in an embodiment of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown herein can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0021] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein.

[0022] In this article, "multiple or several" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0024] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained. Example 1

[0025] To facilitate understanding of this embodiment, the method disclosed in this disclosure will first be described in detail. The execution subject of the method provided in this disclosure is generally a terminal device or other processing device with certain computing capabilities. The terminal device may be a user equipment (UE), mobile device, user terminal, terminal, personal digital assistant device (PDA), handheld device, computer device, etc. In some possible implementations, the method can be implemented by the processor calling computer-readable instructions stored in the memory.

[0026] The method provided in this disclosure embodiment will be described below using a computer device as an example of the executing entity.

[0027] like Figure 1 As shown, one embodiment of the present invention provides a photovoltaic module cleaning method based on multi-cycle weather forecasting, the method comprising the following steps: Step S100: Obtain the physical parameters, historical operating data, and high-precision meteorological forecast data for the target photovoltaic power station in the future preset period; wherein, the physical parameters are used to construct the physical basic model of the power station.

[0028] In step S100 above, the time span of the future preset period of the high-precision meteorological forecast data is not less than 7 days, and includes data on total irradiance (GHI), direct irradiance (DNI), ambient temperature, precipitation and atmospheric pollutant concentration.

[0029] Step S200: Based on the physical model and meteorological forecast data obtained in S100, simulate and calculate the first theoretical power generation sequence under the scenario of no cleaning within a preset period.

[0030] In step S200 above, the simulation calculation is performed in the following manner: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data. A dust loss coefficient model is then introduced to correct the baseline power generation, simulating power generation losses caused by pollution. The dust loss coefficient model is a dynamically updated predictive model based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations.

[0031] Step S300: Select multiple time points within the preset period as candidate cleaning time points. For each candidate cleaning time point, simulate and calculate the second theoretical power generation sequence after cleaning is performed at that time point until the end of the preset period.

[0032] In step S300 above, the simulation calculation is performed in the following manner: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data. A dust loss coefficient model is introduced to correct the baseline power generation, simulating power generation losses caused by pollution. The dust loss coefficient is reset at candidate cleaning time points. The dust loss coefficient model is a dynamically updated predictive model based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations.

[0033] Step S400: Based on the first theoretical power generation sequence obtained in step S200 and the various second theoretical power generation sequences obtained in step S300, and in conjunction with the grid-connected electricity price, calculate the expected additional power generation revenue corresponding to each candidate cleaning time point.

[0034] Step S500: Based on the preset cleaning cost model (grid-connected electricity price, cost per cleaning cycle, etc.) and the expected additional power generation revenue obtained in S400, calculate the expected return on investment (ROI) for each candidate cleaning time point.

[0035] Step S600: From all candidate cleaning time points, select the time point that meets the preset constraints and has the highest expected return on investment as the optimal cleaning time point, and generate a cleaning decision instruction; wherein, the preset constraints include at least meteorological constraints. The meteorological constraints include: no precipitation or precipitation below a threshold (generally set to less than 5 mm of precipitation within 24 hours) on the day of the candidate cleaning time point and within a preset number of days thereafter.

[0036] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic. Example 2

[0037] Based on the same inventive concept, this disclosure also provides a modular system corresponding to the above method. Since the principle of the system in this disclosure for solving the problem is similar to that of the above method in this disclosure, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be described again.

[0038] like Figure 2 As shown, one embodiment of the present invention provides a photovoltaic module cleaning system based on multi-cycle weather forecasting, the system comprising the following modules: The data acquisition module 100 is used to acquire the physical parameters, historical operating data, and high-precision meteorological forecast data for the target photovoltaic power station in the future preset period; among them, the physical parameters are used to construct the physical basic model of the power station.

[0039] The time span of the aforementioned high-precision meteorological forecast data shall be no less than 7 days, and shall include data on total irradiance (GHI), direct irradiance (DNI), ambient temperature, precipitation and atmospheric pollutant concentration.

[0040] The first simulation calculation module 200 is used to simulate and calculate the first theoretical power generation sequence under the unwashed scenario within a preset period, based on the obtained physical foundation model and meteorological forecast data.

[0041] The first simulation calculation module 200 performs simulation calculations in the following manner: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data. A dust loss coefficient model is then introduced to correct the baseline power generation, simulating power generation losses caused by pollution. The dust loss coefficient model is a dynamically updated predictive model based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations.

[0042] The second simulation calculation module 300 is used to take multiple time points within a preset period as candidate cleaning time points, and for each candidate cleaning time point, simulate and calculate the second theoretical power generation sequence after cleaning is performed at that time point until the end of the preset period.

[0043] The second simulation calculation module 300 performs simulation calculations in the following manner: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data. A dust loss coefficient model is introduced to correct the baseline power generation, simulating power generation losses caused by pollution. The dust loss coefficient is reset at candidate cleaning time points. The dust loss coefficient model is a dynamically updated predictive model based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations.

[0044] The power generation revenue calculation module 400 is used to calculate the expected additional power generation revenue corresponding to each candidate cleaning time point based on the first theoretical power generation sequence and each second theoretical power generation sequence, combined with the grid-connected electricity price.

[0045] The ROI calculation module 500 is used to calculate the expected ROI for each candidate cleaning time point based on a preset cleaning cost model and expected additional power generation revenue.

[0046] The instruction generation module 600 is used to select the optimal cleaning time point from all candidate cleaning time points, based on preset constraints and the highest expected return on investment, and to generate a cleaning decision instruction. The preset constraints include at least meteorological constraints. Specifically, the meteorological constraints include: no precipitation or precipitation below a threshold on the day of the candidate cleaning time point and within a preset number of subsequent days.

[0047] For a description of other processing flows of each module in the above system and the interaction flows between modules, please refer to the relevant descriptions in the above method embodiments, which will not be detailed here. Example 3

[0048] like Figure 3 As shown, the specific operation flow of the cleaning optimization method in this embodiment is as follows: S101: System starts up, setting the optimization period (future preset period) to the next 14 days; S102: Collect local real-time weather forecast data, including total irradiance (GHI), direct irradiance (DNI), ambient temperature, precipitation probability, wind speed, PM2.5 concentration and other atmospheric pollutant concentrations, as well as data on light transmittance loss or power generation efficiency loss caused by dust obstruction provided by dedicated sensors (data sources may include power plant SCADA system, environmental monitoring instrument, component dust sensor, etc.). S103: Obtain gridded meteorological data (hourly or daily) for the next 14 days at the power station location via API interface. This data includes precipitation probability and amount (to determine the possibility of natural washing), irradiance (to calculate theoretical power generation), wind speed, humidity, dew point (affecting dust adhesion and drying speed), and atmospheric pollution concentration, such as PM2.5 / PM10 (to predict dust deposition rate). It also calls a pre-built physical data model of the power station, which includes information such as component model, inverter parameters, installation tilt angle, and actual power generation (data source is access to third-party meteorological data API services (such as China Meteorological Administration, Windy, OpenWeatherMap, etc.)). S104: Input power plant parameter configurations based on the current level as the initial state, such as: power plant location, installed capacity, installation tilt angle, module type, feed-in tariff, cost per cleaning cycle, and module contamination loss coefficient (i.e., the percentage decrease in power generation efficiency caused by unit dust density). The above data is sourced from manual input in the system backend or from large database access. S105: Using the current dust level as the initial state, predict the power generation sequence (P_dirty) for the next 14 days if cleaning is not performed. (The system combines data on the number of days without precipitation, wind speed, humidity, and air pollutants, and uses a pollution accumulation model (which can be an empirical formula or a machine learning model) to predict the degree of dust accumulation on the component surface at the end of each day). S106: Iterate through the next 14 days, designating each day as a candidate cleaning day (T_candidate). For each T_candidate, simulate cleaning on that day, resetting the dust loss, and then predicting the power generation sequence from T_candidate to day 14 (P_clean). S107: Calculate the additional power generation revenue generated by each T_candidate: ΔE = (total P_clean - total P_dirty) × feed-in tariff; S108: Calculate the cleaning cost (C) for each T_candidate based on the cleaning cost model (including labor, water costs, equipment wear and tear, etc.); S109: Calculate the return on investment for each T_candidate: ROI = (ΔE - C) / C; S110: Apply constraint filters (automatically avoid dates unsuitable for outdoor operations due to forecasts of rain, strong winds, etc.), for example, exclude candidate days with precipitation forecasts within two days after the cleaning day, exclude candidate days with negative ROI (iterate through each day in the future forecast period (such as the 2nd day, 3rd day... 14th day in the future) and calculate the net benefit that could be obtained if cleaning is carried out on that day). S111: From the remaining candidate days, select the day with the highest ROI as the optimal cleaning day (preferred rule: select the day that brings the maximum positive net benefit as the optimal cleaning day; secondary rule: if the net benefit of all days in the entire forecast period is negative, it is recommended to "not clean" and continue monitoring), and generate a cleaning decision instruction, automatically issue work orders (the system automatically generates operation and maintenance work orders containing information such as the optimal cleaning date, expected recovery benefits, and cost analysis, and pushes the cleaning suggestions to operation and maintenance management personnel through PC dashboards, mobile apps, SMS or email, etc.) or issue alarm prompts to operation and maintenance personnel. Other embodiments

[0049] Based on the same technical concept, embodiments of this application also provide a computer device. (Refer to...) Figure 4 The diagram shown is a structural schematic of a computer device provided in an embodiment of this application, comprising: The system includes a processor 71, a memory 72, and a bus 73. The memory 72 stores machine-readable instructions executable by the processor 71. The processor 71 executes these machine-readable instructions stored in the memory 72. When these machine-readable instructions are executed by the processor 71, the processor 71 can be used to execute... Figure 1 Each step in the method flow.

[0050] The aforementioned memory 72 includes a main memory 721 and an external memory 722. The main memory 721, also known as internal memory, is used to temporarily store the computational data in the processor 71, as well as the data exchanged with external memory such as a hard disk. The processor 71 exchanges data with the external memory 722 through the main memory 721. When the computer device is running, the processor 71 and the memory 72 communicate through the bus 73, so that the processor 71 executes the execution instructions mentioned in the above method embodiments.

[0051] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0052] This disclosure also provides a computer program product carrying program code, the program code including instructions that can be used to execute the steps of the methods described in the above method embodiments.

[0053] The computer program product can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0055] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0056] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0057] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0058] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the user through pop-up information or by asking the user to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0059] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions 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 this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A photovoltaic module cleaning method based on multi-period weather forecasting, characterized in that, include: The physical parameters, historical operating data, and high-precision meteorological forecast data for the future preset period of the target photovoltaic power station are obtained. The physical parameters are used to construct the physical basic model of the power station. Based on the physical model and the meteorological forecast data, the first theoretical power generation sequence under the non-cleaning scenario within the preset period is simulated and calculated. Multiple time points within the preset period are used as candidate cleaning time points. For each candidate cleaning time point, the second theoretical power generation sequence is simulated and calculated after cleaning is performed at that time point until the end of the preset period. Based on the first theoretical power generation sequence and each of the second theoretical power generation sequences, and in conjunction with the on-grid electricity price, the expected additional power generation revenue corresponding to each candidate cleaning time point is calculated respectively. Based on the preset cleaning cost model and the expected additional power generation revenue, the expected return on investment (ROI) for each candidate cleaning time point is calculated; and From all candidate cleaning time points, the time point that meets the preset constraints and has the highest expected return on investment is selected as the optimal cleaning time point, and a cleaning decision instruction is generated.

2. The method according to claim 1, characterized in that, The high-precision meteorological forecast data has a future preset period of no less than 7 days, and the data includes at least total irradiance, direct irradiance, ambient temperature, precipitation and atmospheric pollutant concentration data.

3. The method according to claim 1, characterized in that, The steps for simulating the first and second theoretical power generation sequences both include: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data; a dust loss coefficient model is introduced to correct the baseline power generation to simulate power generation loss caused by pollution. The steps for simulating and calculating the second theoretical power generation sequence also include: The dust loss coefficient is reset at the corresponding candidate cleaning time point.

4. The method according to claim 3, characterized in that, The dust loss coefficient model is a prediction model trained based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations.

5. The method according to claim 1, characterized in that, The preset constraints include meteorological constraints, which require that there is no precipitation or the amount of precipitation is less than a threshold on the day of the candidate cleaning time and within the subsequent preset time.

6. A photovoltaic module cleaning system based on multi-period weather forecasting, characterized in that, include: The data acquisition module is used to acquire the physical parameters, historical operating data, and high-precision meteorological forecast data for the target photovoltaic power station in the future preset period; among them, the physical parameters are used to construct the physical basic model of the power station. Among them, the future preset period of the above-mentioned high-precision meteorological forecast data is no less than 7 days, and the data includes total irradiance, direct irradiance, ambient temperature, precipitation and atmospheric pollutant concentration data. The first simulation calculation module is used to simulate and calculate the first theoretical power generation sequence under the unwashed scenario within a preset period, based on the obtained physical foundation model and meteorological forecast data. The first simulation calculation module performs simulation calculations in the following manner: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data. A dust loss coefficient model is introduced to correct the baseline power generation to simulate power generation loss caused by pollution. The dust loss coefficient model is a forecast model that is dynamically updated based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations. The second simulation calculation module is used to take multiple time points within a preset period as candidate cleaning time points, and for each candidate cleaning time point, simulate and calculate the second theoretical power generation sequence after cleaning is performed at that time point until the end of the preset period. The second simulation module described above performs simulation calculations in the following manner: Using the aforementioned physical model, the baseline power generation under ideal clean conditions is calculated based on meteorological forecast data. A dust loss coefficient model is introduced to correct the baseline power generation to simulate power generation loss caused by pollution. The dust loss coefficient is reset at candidate cleaning time points. The dust loss coefficient model is a prediction model that is dynamically updated based on historical data on days without precipitation, wind speed, and atmospheric pollutant concentrations. The power generation revenue calculation module is used to calculate the expected additional power generation revenue corresponding to each candidate cleaning time point based on the first theoretical power generation sequence and each second theoretical power generation sequence, combined with the on-grid electricity price. The return on investment (ROI) calculation unit is used to calculate the expected ROI for each candidate cleaning time point based on a preset cleaning cost model and expected additional power generation revenue; and The instruction generation module is used to select the optimal cleaning time point from all candidate cleaning time points, which meets the preset constraints and has the highest expected return on investment, and generate a cleaning decision instruction; wherein, the preset constraints include at least meteorological constraints; wherein, the meteorological constraints include: no precipitation or precipitation below a threshold on the day of the candidate cleaning time point and within a preset number of days thereafter.

7. The system according to claim 6, characterized in that, It also includes a physical fundamental model building module, which is used to build and maintain the physical fundamental model based on the physical parameters.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 5.

10. A computer program product carrying program code, the program code including instructions that can be used to implement the method as described in any one of claims 1 to 5.

Images