Photovoltaic module cleaning method based on meteorological data

Abstract

The invention provides a photovoltaic module cleaning method based on meteorological data, and belongs to the technical field of photovoltaic module cleaning, and the method comprises the steps: 1, obtaining the structure of a target photovoltaic module, and determining a sensor and a device for monitoring a fault signal; 2, constructing a data acquisition network, and collecting real-time operation data of the target photovoltaic panel; 3, analyzing the real-time operation data according to a real-time data processing algorithm, identifying power generation abnormity, and determining a fault mode of the photovoltaic module; 4, obtaining weather forecast information in the next 24 hours, and determining the influence of weather conditions on the power generation efficiency based on the component power generation performance model; 5, determining the energy storage balance according to the real-time state of the photovoltaic energy storage system, and determining the expected photoelectric conversion efficiency and the gain after cleaning; and 6, making a cleaning strategy according to the fault mode and the energy storage condition of the photovoltaic module. The problem that the performance of the module is reduced due to excessive or insufficient cleaning possibly caused by accumulation of sediments on the surface of the photovoltaic module is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic component cleaning, and in particular to a photovoltaic component cleaning method based on meteorological data. Background Art

[0002] With the rapid development of the photovoltaic industry, the installation volume of photovoltaic modules has increased year by year.

[0003] Traditional PV module cleaning methods tend to ignore important factors related to meteorological data, such as wind speed, humidity, and atmospheric particulate matter concentration, resulting in the continuous accumulation of deposits on the surface of PV modules. At the same time, traditional methods usually rely on fixed schedules or thresholds and cannot cope with changing weather conditions and module conditions. Excessive or insufficient cleaning may occur, resulting in reduced module performance or even damage.

[0004] Therefore, the present invention proposes a photovoltaic module cleaning method based on meteorological data. Summary of the Invention

[0005] The present invention provides a photovoltaic module cleaning method based on meteorological data to address the problem in the prior art that important factors related to meteorological data are easily overlooked, resulting in the continuous accumulation of deposits on the surface of photovoltaic modules. At the same time, traditional methods usually rely on fixed schedules or thresholds and cannot cope with changing weather conditions and module conditions. Excessive or insufficient cleaning may occur, resulting in decreased module performance or even damage.

[0006] In one aspect, the present invention provides a photovoltaic module cleaning method based on meteorological data, characterized by comprising:

[0007] Step 1: Obtain the structure of the target photovoltaic module, and determine the sensor and online monitoring equipment for monitoring fault signals based on the structure;

[0008] Step 2: Build a data acquisition network to collect real-time operating data of the target photovoltaic panels based on sensors and online monitoring equipment that monitors fault signals;

[0009] Step 3: Analyze the real-time operating data according to a real-time data processing algorithm, identify power generation anomalies based on the analysis results, and determine the failure mode of the photovoltaic module based on the power generation anomaly based on a deep learning model;

[0010] Step 4: Obtain weather forecast information for the next 24 hours, and determine the impact of weather conditions on photovoltaic module power generation efficiency based on the module power generation performance model according to the weather forecast information;

[0011] Step 5: Determine the energy storage balance based on the real-time status of the photovoltaic energy storage system, and determine the expected photovoltaic conversion efficiency and gain after cleaning based on the expected power generation;

[0012] Step 6: Formulate a cleaning strategy based on the photovoltaic module failure mode, the impact of weather conditions on the photovoltaic module power generation efficiency, and the energy storage status, and clean the photovoltaic module according to the cleaning strategy.

[0013] According to a photovoltaic module cleaning method based on meteorological data provided by the present invention, the structure of a target photovoltaic module is obtained, and a sensor and an online monitoring device for monitoring fault signals are determined based on the structure, including:

[0014] Obtaining the working principle and technical characteristics of the target photovoltaic module, and determining the structure of the target photovoltaic module based on the working principle and technical characteristics;

[0015] Determine the key parameters that need to be monitored based on the structure of the target PV module, the working principle of the PV module, and the usage scenario;

[0016] Obtain parameter types and parameter quantities of key parameters, and determine sensors based on the parameter types and parameter quantities;

[0017] Obtain the sensor type and obtain the online monitoring device for monitoring fault signals based on the key parameters that need to be monitored.

[0018] According to a photovoltaic module cleaning method based on meteorological data provided by the present invention, a data acquisition network is constructed, and real-time operating data of a target photovoltaic panel is collected based on sensors and online monitoring equipment that monitors fault signals on the data acquisition network, including:

[0019] Obtain target data acquisition equipment based on target PV panels and working environment;

[0020] Determine the data collection frequency and time point based on the target data collection equipment and the data coverage of the collection;

[0021] Build a data collection device network based on wireless mode according to the data collection frequency and data collection time point;

[0022] The real-time operating data of the target photovoltaic panel is collected based on the data acquisition network, sensors and online monitoring equipment that monitors fault signals.

[0023] According to a photovoltaic module cleaning method based on meteorological data provided by the present invention, the real-time operating data is analyzed according to a real-time data processing algorithm, power generation anomalies are identified according to the analysis results, and a photovoltaic module failure mode is determined based on the power generation anomaly based on a deep learning model, including:

[0024] Analyzing the real-time running data according to a real-time data processing algorithm, and determining the indicators of cluster centroid distance and average distance within the cluster according to the analysis results;

[0025] determining abnormal operation data according to the indicator, obtaining an abnormality type of the abnormal operation data, and identifying power generation abnormality according to the abnormality type;

[0026] Acquire deep learning models based on different model architectures and parameter configurations according to actual application scenarios and the characteristics of abnormal operation data;

[0027] A photovoltaic component failure mode is determined based on a deep learning model according to the power generation anomaly.

[0028] According to a photovoltaic module cleaning method based on meteorological data provided by the present invention, weather forecast information for the next 24 hours is obtained, and the impact of weather conditions on photovoltaic module power generation efficiency is determined based on the module power generation performance model according to the weather forecast information, including:

[0029] Obtain weather forecast information for the next 24 hours based on the Meteorological Bureau data source;

[0030] Extracting features related to photovoltaic module power generation efficiency based on weather forecast information using a machine learning algorithm;

[0031] Build a module power generation performance model based on historical meteorological data and characteristics related to PV module power generation efficiency, and evaluate the model based on evaluation indicators;

[0032] Determine the power generation efficiency of the target PV modules under different weather conditions based on the evaluated model and the weather forecast information for the next 24 hours;

[0033] The influence of weather conditions on the power generation efficiency of the photovoltaic module is determined based on the power generation efficiency.

[0034] According to a photovoltaic module cleaning method based on meteorological data provided by the present invention, the energy storage balance is determined according to the real-time status of the photovoltaic energy storage system, and the expected photoelectric conversion efficiency and the gain after cleaning are determined in combination with the expected power generation, including:

[0035] monitoring the status of the photovoltaic energy storage system in real time according to the control system, obtaining the current capacity of the photovoltaic energy storage system according to the real-time status, and determining the energy storage balance according to the current capacity;

[0036] Determine the expected power generation based on the efficiency of the photovoltaic panels according to the energy storage balance, and determine the expected photovoltaic conversion efficiency based on the expected power generation and weather conditions;

[0037] Obtain the efficiency of the photovoltaic cell and determine the gain after cleaning in combination with the expected photoelectric conversion efficiency.

[0038] According to a photovoltaic module cleaning method based on meteorological data provided by the present invention, a cleaning strategy is formulated according to the photovoltaic module failure mode, the impact of weather conditions on the photovoltaic module power generation efficiency, and the energy storage status, and the photovoltaic module is cleaned according to the cleaning strategy, including:

[0039] locating the fault and determining the cause of the fault according to the photovoltaic module failure mode;

[0040] Determine the degree of impact based on the impact of weather conditions on the power generation efficiency of photovoltaic modules;

[0041] Cleaning information is determined according to the cause of the fault, the degree of impact, and the energy storage status, a cleaning strategy is formulated according to the cleaning information, and the photovoltaic components are cleaned according to the cleaning strategy.

[0042] According to the present invention, a photovoltaic module cleaning method based on meteorological data is provided, which realizes cleaning of the photovoltaic module according to a cleaning strategy, including:

[0043] Determine the stain type and stain area, determine the stain step characteristics based on the stain type and stain area, and determine the surface coverage damage characteristics of the photovoltaic module based on the stain distribution characteristics;

[0044] Determine the three-dimensional characteristic matrix of the surface grain size of the photovoltaic module according to the surface coverage damage characteristics of the photovoltaic module;

[0045] Determining a cleaning amplitude characteristic matrix for the surface of the photovoltaic module based on a three-dimensional characteristic matrix of particle size and a three-dimensional matrix of standard cleanliness of the surface of the photovoltaic module;

[0046] Obtaining dust drift information in the operating environment of the photovoltaic module, and determining the daily dust deposition amount variable and the weekly dust deposition amount variable of the photovoltaic module based on the dust drift information;

[0047] Calculate the increasing index between the daily dust deposition variable and the weekly dust deposition variable, and determine the power generation efficiency attenuation rate of the photovoltaic module based on the increasing index and the cleaning amplitude characteristic matrix of the photovoltaic module surface;

[0048] Collecting operating parameter information of photovoltaic modules, and dividing the photovoltaic modules into different regional performance matrices according to the operating parameter information and preset performance classification standards;

[0049] Based on the power generation efficiency attenuation rate of photovoltaic modules and the regional performance matrix, multiple effective cleaning frameworks and multiple cleaning time points are planned without affecting power generation efficiency;

[0050] Determine multiple effective cleaning frameworks and multiple cleaning time points under the cleaning strategy for multiple cleaning yields;

[0051] The target cleaning time point with the highest cleaning yield and the target effective cleaning frame are selected as the optimal cleaning time point and the optimal cleaning position area, and the optimal cleaning position area of the photovoltaic module is cleaned at the optimal cleaning time point based on the cleaning strategy.

[0052] Compared with the prior art, the present invention has the following advantages:

[0053] The real-time operating data of the target photovoltaic panels is used to determine the failure mode of photovoltaic modules, the impact of weather conditions on the power generation efficiency of photovoltaic modules is determined, and a cleaning strategy is formulated in combination with the energy storage status of the photovoltaic modules. Important factors related to meteorological data, such as wind speed, humidity, and atmospheric particulate matter concentration, are not easily ignored to avoid the continuous accumulation of deposits on the surface of photovoltaic modules. At the same time, there is no need to rely on fixed schedules or thresholds, and it can cope with changing weather conditions and module conditions, avoid excessive or insufficient cleaning, improve module performance, and reduce the probability of photovoltaic module damage. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 1 is a flow chart of a photovoltaic module cleaning method based on meteorological data provided by an embodiment of the present invention;

[0056] Figure 2 It is a flow chart of an online monitoring device for determining sensors according to a structure and monitoring fault signals provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0058] Example 1:

[0059] The embodiment of the present invention provides a photovoltaic module cleaning method based on meteorological data, such as Figure 1 As shown, the method mainly includes the following steps:

[0060] Step 1: Obtain the structure of the target photovoltaic module, and determine the sensor and online monitoring equipment for monitoring fault signals based on the structure;

[0061] Step 2: Build a data acquisition network to collect real-time operating data of the target photovoltaic panels based on sensors and online monitoring equipment that monitors fault signals;

[0062] Step 3: Analyze the real-time operating data according to a real-time data processing algorithm, identify power generation anomalies based on the analysis results, and determine the failure mode of the photovoltaic module based on the power generation anomaly based on a deep learning model;

[0063] Step 4: Obtain weather forecast information for the next 24 hours, and determine the impact of weather conditions on photovoltaic module power generation efficiency based on the module power generation performance model according to the weather forecast information;

[0064] Step 5: Determine the energy storage balance based on the real-time status of the photovoltaic energy storage system, and determine the expected photovoltaic conversion efficiency and gain after cleaning based on the expected power generation;

[0065] Step 6: Formulate a cleaning strategy based on the photovoltaic module failure mode, the impact of weather conditions on the photovoltaic module power generation efficiency, and the energy storage status, and clean the photovoltaic module according to the cleaning strategy.

[0066] In this embodiment, the structure of the photovoltaic module includes:

[0067] Glass components: used to protect internal electronic components from harsh environments and provide a good optical surface to absorb more sunlight.

[0068] Backsheet: The backsheet is mainly used to conduct current and release electrons generated by the photovoltaic effect from the battery.

[0069] N-layer or P-layer cells: N-layer cells mainly absorb positive charges, while P-layer cells absorb negative charges.

[0070] Bus: The bus is located on the back of the battery cell and is responsible for collecting the current generated by the battery cell and introducing the current into the external circuit.

[0071] In this embodiment, the sensor may be: a voltage sensor, a current sensor, or a temperature sensor.

[0072] In this embodiment, the online monitoring device for monitoring the fault signal may be: a light meter or a mechanical safety device.

[0073] In this embodiment, the real-time operating data of the photovoltaic panel may include: power, operating temperature, operating current, and operating voltage.

[0074] In this embodiment, the real-time data processing algorithm refers to the K-means clustering algorithm.

[0075] In this embodiment, the photovoltaic module failure mode may be: cell damage, cable or connector damage, or control chip failure.

[0076] In this embodiment, the weather forecast information includes: date and time, location, weather phenomena, and wind force level.

[0077] In this embodiment, the photovoltaic module power generation performance model refers to a model used to predict and evaluate the power generation performance of the photovoltaic module under different environmental conditions.

[0078] In this embodiment, the energy storage balance refers to the energy stored in the energy storage system.

[0079] In this embodiment, the cleaning strategy refers to formulating different cleaning methods and tools for different types of dirt and dust on the surface of the photovoltaic module.

[0080] The beneficial effects of the above technical solution are: determining the failure mode of photovoltaic modules through the real-time operating data of the target photovoltaic panels, determining the impact of weather conditions on the power generation efficiency of photovoltaic modules, and formulating cleaning strategies in combination with the energy storage conditions of photovoltaic modules. It is not easy to ignore important factors related to meteorological data, such as wind speed, humidity, and atmospheric particulate matter concentration, to avoid the continuous accumulation of deposits on the surface of photovoltaic modules. At the same time, it does not need to rely on fixed schedules or thresholds, can cope with changing weather conditions and module conditions, avoid excessive or insufficient cleaning, improve module performance, and reduce the probability of photovoltaic module damage.

[0081] Example 2:

[0082] Based on Example 1, the embodiment of the present invention obtains the structure of the target photovoltaic module, and determines the sensor and the online monitoring device for monitoring the fault signal according to the structure, such as Figure 2 Shown, including:

[0083] S01: Obtaining the working principle and technical characteristics of the target photovoltaic module, and determining the structure of the target photovoltaic module based on the working principle and technical characteristics;

[0084] S02: Determine the key parameters that need to be monitored based on the structure of the target PV module, the working principle of the PV module, and the usage scenario;

[0085] S03: Obtain parameter type and parameter quantity of key parameters, and determine the sensor according to the parameter type and parameter quantity;

[0086] S04: Obtain the sensor type, and obtain an online monitoring device for monitoring fault signals based on key parameters that need to be monitored.

[0087] In this embodiment, a photovoltaic module is a device that converts solar energy into electrical energy. Its working principle is based on the photoelectric effect:

[0088] Photon absorption: Photons in sunlight are absorbed by the photosensitive material (usually silicon) of the photovoltaic module.

[0089] Electron transition: When photons are absorbed, the free electrons in the silicon atoms gain enough energy to jump from the valence band to the conduction band, separating the electrons and holes.

[0090] Electron-hole recombination: The separated free electrons and holes recombine rapidly through internal mechanisms, releasing a large amount of heat energy.

[0091] In this embodiment, the technical features of the photovoltaic module may be: high photoelectric conversion efficiency, environmental protection and pollution-free, and reversibility.

[0092] In this embodiment, the structure of the photovoltaic module includes:

[0093] Glass components: used to protect internal electronic components from harsh environments and provide a good optical surface to absorb more sunlight.

[0094] Backsheet: The backsheet is mainly used to conduct current and release electrons generated by the photovoltaic effect from the battery.

[0095] N-layer or P-layer cells: N-layer cells mainly absorb positive charges, while P-layer cells absorb negative charges.

[0096] Bus: The bus is located on the back of the battery cell and is responsible for collecting the current generated by the battery cell and introducing the current into the external circuit.

[0097] In this embodiment, key parameters include: temperature, voltage, current, and power.

[0098] The beneficial effects of the above technical solution are: determining key parameters based on the structure of the target photovoltaic module combined with the working principle and usage scenario of the module, thereby determining the sensors and online monitoring equipment for monitoring fault signals, which can provide real-time and accurate data, thereby enabling a deeper understanding of the status of the module and timely detection of module problems, which can improve the efficiency of data acquisition and, at the same time, ensure the safe use of photovoltaic modules.

[0099] Example 3:

[0100] Based on Example 2, this embodiment of the present invention constructs a data acquisition network, and collects real-time operating data of the target photovoltaic panel based on sensors and online monitoring equipment that monitors fault signals on the data acquisition network, including:

[0101] Obtain target data acquisition equipment based on target PV panels and working environment;

[0102] Determine the data collection frequency and time point based on the target data collection equipment and the data coverage of the collection;

[0103] Build a data collection device network based on wireless mode according to the data collection frequency and data collection time point;

[0104] The real-time operating data of the target photovoltaic panel is collected based on the data acquisition network, sensors and online monitoring equipment that monitors fault signals.

[0105] In this embodiment, the target data acquisition equipment includes: photovoltaic module testing equipment, remote monitoring system, and energy management system.

[0106] In this embodiment, the data coverage refers to the area or scene that can be covered by the data acquisition device.

[0107] In this embodiment, the data collection frequency refers to the time within which data is collected from the photovoltaic module.

[0108] In this embodiment, the data collection time point refers to the specific moment when data collection is performed.

[0109] In this embodiment, the wireless method refers to a method of realizing information transmission through wireless technology, which can perform remote data transmission without using a wired connection.

[0110] In this embodiment, the data acquisition device network is a technology that connects various devices to the Internet to collect and analyze various real-time data in real time.

[0111] In this embodiment, the sensors include: a temperature sensor, a voltage sensor, a current sensor, and a power sensor.

[0112] In this embodiment, the online monitoring device for monitoring the fault signal may be: a light meter or a mechanical safety device.

[0113] In this embodiment, the real-time operating data of the photovoltaic panel may include: power, operating temperature, operating current, and operating voltage.

[0114] The beneficial effect of the above technical solution is: by building a data acquisition device network through data acquisition frequency and data acquisition time point, the real-time operation data of the photovoltaic panels can be obtained, which can realize real-time and accurate monitoring and management of various environmental factors and ensure the real-time nature of the data.

[0115] Example 4:

[0116] Based on Example 3, this embodiment of the present invention analyzes the real-time operating data according to a real-time data processing algorithm, identifies power generation anomalies according to the analysis results, and determines a photovoltaic module failure mode based on the power generation anomaly based on a deep learning model, including:

[0117] Analyzing the real-time running data according to a real-time data processing algorithm, and determining the indicators of cluster centroid distance and average distance within the cluster according to the analysis results;

[0118] determining abnormal operation data according to the indicator, obtaining an abnormality type of the abnormal operation data, and identifying power generation abnormality according to the abnormality type;

[0119] Acquire deep learning models based on different model architectures and parameter configurations according to actual application scenarios and the characteristics of abnormal operation data;

[0120] A photovoltaic component failure mode is determined based on a deep learning model according to the power generation anomaly.

[0121] In this embodiment, the real-time data processing algorithm refers to the K-means clustering algorithm.

[0122] In this embodiment, the cluster centroid distance is mainly used to describe the centroid position in the clustering algorithm and is the average value of all data.

[0123] In this embodiment, the intra-cluster average distance measures the average distance between the points inside each cluster and the center of the cluster.

[0124] In this embodiment, the abnormal operation data may be: abnormal power output of the photovoltaic module, abnormal temperature of the photovoltaic module.

[0125] In this embodiment, the abnormal types of abnormal operation data include: numerical abnormality, missing abnormality, format abnormality, and logical abnormality.

[0126] In this embodiment, power generation anomalies include: over-power generation, under-power generation, and low efficiency.

[0127] In this embodiment, the model architecture can be: convolutional neural network, recurrent neural network, long short-term memory network.

[0128] In this embodiment, the parameter configuration includes:

[0129] Input layer: The size of the input data is the same as the size of the original input data.

[0130] Convolutional layer: parameters such as convolution kernel size, stride, zero padding, etc.

[0131] Fully Connected Layers: The number and size of fully connected layers.

[0132] In this embodiment, the photovoltaic module failure mode may be: cell damage, cable or connector damage, or control chip failure.

[0133] The beneficial effects of the above technical solution are: by analyzing the real-time operation data according to the real-time data processing algorithm, obtaining abnormal data and the type of abnormal data, it is possible to effectively monitor and warn of abnormal situations, avoid or reduce the occurrence of failures and accidents during operation, and ensure the continuity and stability of operation. Furthermore, the failure mode of the component is determined according to the deep learning model, which can improve the accuracy and reliability of the determination results.

[0134] Example 5:

[0135] Based on Example 4, this embodiment of the present invention obtains weather forecast information for the next 24 hours, and determines the impact of weather conditions on photovoltaic module power generation efficiency based on the module power generation performance model according to the weather forecast information, including:

[0136] Obtain weather forecast information for the next 24 hours based on the Meteorological Bureau data source;

[0137] Extracting features related to photovoltaic module power generation efficiency based on weather forecast information using a machine learning algorithm;

[0138] Build a module power generation performance model based on historical meteorological data and characteristics related to PV module power generation efficiency, and evaluate the model based on evaluation indicators;

[0139] Determine the power generation efficiency of the target PV modules under different weather conditions based on the evaluated model and the weather forecast information for the next 24 hours;

[0140] The influence of weather conditions on the power generation efficiency of the photovoltaic module is determined based on the power generation efficiency.

[0141] In this embodiment, the weather forecast information includes: date and time, location, weather phenomena, and wind force level.

[0142] In this embodiment, the machine learning algorithm may be: linear regression, support vector machine, neural network.

[0143] In this embodiment, the characteristics related to the power generation efficiency of the photovoltaic module include: light intensity, temperature, dust and obstructions, and weather conditions.

[0144] In this embodiment, the photovoltaic module power generation performance model refers to a model used to predict and evaluate the power generation performance of the photovoltaic module under different environmental conditions.

[0145] In this embodiment, the evaluation indicators include: accuracy, precision, and F1 score.

[0146] In this embodiment, the power generation efficiency of the photovoltaic module refers to the ability of the photovoltaic module to convert solar energy into electrical energy.

[0147] The beneficial effects of the above technical solution are: constructing a component power generation performance model based on historical meteorological data and characteristics related to the power generation efficiency of photovoltaic modules, thereby determining the power generation efficiency of the target photovoltaic modules under different weather conditions, noting the impact of environmental conditions on power generation efficiency, avoiding the deposition of sediment on the surface of the modules, and thus adjusting the modules to improve the performance of the photovoltaic modules.

[0148] Example 6:

[0149] Based on Example 5, this embodiment of the present invention determines the energy storage balance based on the real-time status of the photovoltaic energy storage system, and determines the expected photoelectric conversion efficiency and the gain after cleaning in combination with the expected power generation, including:

[0150] monitoring the status of the photovoltaic energy storage system in real time according to the control system, obtaining the current capacity of the photovoltaic energy storage system according to the real-time status, and determining the energy storage balance according to the current capacity;

[0151] Determine the expected power generation based on the efficiency of the photovoltaic panels according to the energy storage balance, and determine the expected photovoltaic conversion efficiency based on the expected power generation and weather conditions;

[0152] Obtain the efficiency of the photovoltaic cell and determine the gain after cleaning in combination with the expected photoelectric conversion efficiency.

[0153] In this embodiment, the status of the photovoltaic energy storage system refers to the operating status of the photovoltaic energy storage system, including information on the system's working status, performance indicators, energy output, maintenance status, and other aspects.

[0154] In this embodiment, the energy storage balance refers to the energy stored in the energy storage system.

[0155] In this embodiment, the efficiency of a photovoltaic panel refers to the ability of a solar cell to convert sunlight energy into electrical energy.

[0156] In this embodiment, the expected power generation refers to the power that the photovoltaic power station is expected to generate within a certain period of time (eg, one year).

[0157] In this embodiment, the expected photoelectric conversion efficiency refers to the most ideal photoelectric conversion efficiency that can be achieved by the photovoltaic system under specific conditions (such as geographical location, weather conditions, dust, etc.).

[0158] In this embodiment, the efficiency of a photovoltaic cell refers to the ability of the photovoltaic cell to convert light energy into electrical energy.

[0159] In this embodiment, the gain after cleaning refers to the phenomenon that the photoelectric conversion efficiency of the photovoltaic cell is improved after the photovoltaic cell is cleaned compared with that before cleaning.

[0160] The beneficial effects of the above technical solution are: by determining the energy storage balance based on the real-time status of the photovoltaic energy storage system, the remaining capacity of the photovoltaic energy storage system can be evaluated, more efficient system management can be achieved, and the stability and reliability of the system can be improved. Furthermore, by combining the expected power generation to determine the expected photoelectric conversion efficiency and the gain after cleaning, the cleaning process can be more effectively controlled to minimize energy waste.

[0161] Example 7:

[0162] Based on Example 6, this embodiment of the present invention formulates a cleaning strategy based on the photovoltaic module failure mode, the impact of weather conditions on the photovoltaic module power generation efficiency, and the energy storage status, and implements cleaning of the photovoltaic module according to the cleaning strategy, including:

[0163] locating the fault and determining the cause of the fault according to the photovoltaic module failure mode;

[0164] Determine the degree of impact based on the impact of weather conditions on the power generation efficiency of photovoltaic modules;

[0165] Cleaning information is determined according to the cause of the fault, the degree of impact, and the energy storage status, a cleaning strategy is formulated according to the cleaning information, and the photovoltaic components are cleaned according to the cleaning strategy.

[0166] In this embodiment, the photovoltaic module failure mode may be: cell damage, cable or connector damage, or control chip failure.

[0167] In this embodiment, fault location refers to determining the cause of a component failure and finding a solution to the problem when the component fails.

[0168] In this embodiment, the fault cause is determined, for example: when the fault is battery cell damage, the fault cause may be physical damage to the battery cell, chemical contamination, or circuit failure.

[0169] In this embodiment, the degree of impact can be: slight impact or severe impact.

[0170] In this embodiment, the cleaning information includes: cleaning frequency and cleaning time.

[0171] In this embodiment, the cleaning strategy refers to formulating different cleaning methods and tools for different types of dirt and dust on the surface of the photovoltaic module.

[0172] The beneficial effects of the above technical solution are: determining the cleaning strategy according to the cause of the fault, the degree of impact and the energy storage status can improve the targeted cleaning, avoid the problems of insufficient or excessive cleaning, improve the performance of the components, and ensure that the components are not damaged.

[0173] Example 8:

[0174] Based on Example 7, the embodiment of the present invention implements cleaning of photovoltaic modules according to a cleaning strategy, including:

[0175] Determine the type and area of the stain, determine the stain distribution characteristics based on the stain type and area, and determine the surface coverage damage characteristics of the photovoltaic module based on the stain distribution characteristics;

[0176] Determine the three-dimensional characteristic matrix of the surface grain size of the photovoltaic module according to the surface coverage damage characteristics of the photovoltaic module;

[0177] Determining a cleaning amplitude characteristic matrix for the surface of the photovoltaic module based on a three-dimensional characteristic matrix of particle size and a three-dimensional matrix of standard cleanliness of the surface of the photovoltaic module;

[0178] Obtaining dust drift information in the operating environment of the photovoltaic module, and determining the daily dust deposition amount variable and the weekly dust deposition amount variable of the photovoltaic module based on the dust drift information;

[0179] Obtaining the increasing index between the daily dust deposition variable and the weekly dust deposition variable, and determining the power generation efficiency attenuation rate of the photovoltaic module based on the increasing index and the cleaning amplitude characteristic matrix of the photovoltaic module surface;

[0180] Collecting operating parameter information of photovoltaic modules, and dividing the photovoltaic modules into different regional performance matrices according to the operating parameter information and preset performance classification standards;

[0181] Based on the power generation efficiency attenuation rate of photovoltaic modules and the regional performance matrix, multiple effective cleaning frameworks and multiple cleaning time points are planned without affecting power generation efficiency;

[0182] Determine multiple effective cleaning frameworks and multiple cleaning time points under the cleaning strategy for multiple cleaning yields;

[0183] The target cleaning time point with the highest cleaning yield and the target effective cleaning frame are selected as the optimal cleaning time point and the optimal cleaning position area, and the optimal cleaning position area of the photovoltaic module is cleaned at the optimal cleaning time point based on the cleaning strategy.

[0184] In this embodiment, the types of stains include accumulation of dust, grease, chemicals, branches, leaves and other plant debris.

[0185] In this embodiment, the stain area refers to the total area of the contaminants on the surface of the photovoltaic module.

[0186] In this embodiment, the stain distribution characteristics may be: patchy distribution, strip-like distribution, sheet-like distribution, and network-like distribution.

[0187] In this embodiment, the damage characteristics of the photovoltaic module surface cover refer to various forms of scratches, damages, and attachments that appear on the surface of the photovoltaic module. The damage characteristics may be: scratches, wear, corrosion, and dirt.

[0188] In this embodiment, the three-dimensional feature matrix is a way to describe the particle size on the surface of the photovoltaic module, and represents the size, shape and distribution of the particles through size dimension, shape dimension and distribution dimension.

[0189] In this embodiment, the three-dimensional matrix of standard cleanliness of the photovoltaic module surface is a description of the cleanliness of the photovoltaic module surface, and represents the cleanliness of the photovoltaic module surface through three dimensions, including:

[0190] Optical performance dimension: Indicates the numerical range of component surface reflectivity, absorptivity, and transmittance, reflecting the content and type of surface contaminants. The better the optical performance, the cleaner the component surface.

[0191] Visible light pollution: This dimension indicates the ability of visible light to penetrate the module surface, affecting the module's photoelectric conversion efficiency. When surface contamination is heavy, the degree of visible light absorption or scattering is increased, resulting in reduced light intensity on the module surface, thus affecting photoelectric conversion efficiency.

[0192] Particle concentration dimension: Indicates the concentration of particles on the component surface, reflecting the cleanliness of the component surface. The higher the particle concentration, the dirtier the component surface.

[0193] In this embodiment, the cleaning amplitude characteristic matrix of the photovoltaic module surface is an evaluation tool for the cleaning effect of the photovoltaic module surface, and the quality of the cleaning amplitude is determined by evaluating the changes in the photovoltaic module surface before and after cleaning.

[0194] In this embodiment, the dust drift information refers to data on the distribution and movement of dust particles in the air acquired by sensors or other monitoring equipment under a specific environment, including the diffusion path, residence time, and concentration of dust particles.

[0195] In this embodiment, the daily dust deposition amount variable refers to the change in the amount and distribution of suspended particulate matter in the air deposited on the surface of the photovoltaic module within a day.

[0196] In this embodiment, the weekly dust deposition amount variable refers to the change in the amount and distribution of suspended particulate matter in the air deposited on the surface of the photovoltaic module within a week.

[0197] In this embodiment, the incremental index is used to describe the incremental change relationship between the daily dust deposition amount variable and the weekly dust deposition amount variable.

[0198] In this embodiment, the power generation efficiency attenuation rate of the photovoltaic module refers to the speed at which the power generation efficiency of the photovoltaic module decreases due to factors such as light intensity and temperature within a certain period of time.

[0199] In this embodiment, the preset performance classification standards may be: conversion efficiency, light intensity, and temperature.

[0200] In this embodiment, different regional performance matrices refer to regional difference evaluation matrices formed by comprehensively evaluating and comparing the photovoltaic power generation efficiency and operation and maintenance costs of each region based on factors such as light and temperature in different regions.

[0201] In this embodiment, the cleaning yield rate refers to the ratio between the electricity revenue and cost generated by the method of improving the conversion efficiency of photovoltaic modules and reducing the overall operating cost of the photovoltaic system through cleaning and maintenance.

[0202] The beneficial effects of the above technical solution are: selecting the target cleaning time point and target effective cleaning frame with the highest cleaning yield as the optimal cleaning time point and the optimal cleaning position area, and cleaning the optimal cleaning position area of the photovoltaic module, which can ensure the power generation efficiency of the photovoltaic module, avoid excessive cleaning or insufficient cleaning, and improve the cleaning efficiency and cleaning speed.

[0203] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A photovoltaic module cleaning method based on meteorological data, characterized in that: include: Step 1: Obtain the structure of the target photovoltaic module, and determine the sensor and online monitoring equipment for monitoring fault signals based on the structure; Step 2: Build a data acquisition network to collect real-time operating data of the target photovoltaic panels based on sensors and online monitoring equipment that monitors fault signals; Step 3: Analyze the real-time operating data according to a real-time data processing algorithm, identify power generation anomalies based on the analysis results, and determine the failure mode of the photovoltaic module based on the power generation anomaly based on a deep learning model; Step 4: Obtain weather forecast information for the next 24 hours, and determine the impact of weather conditions on photovoltaic module power generation efficiency based on the module power generation performance model according to the weather forecast information; Step 5: Determine the energy storage balance based on the real-time status of the photovoltaic energy storage system, and determine the expected photovoltaic conversion efficiency and gain after cleaning based on the expected power generation; Step 6: Formulate a cleaning strategy based on the photovoltaic module failure mode, the impact of weather conditions on the photovoltaic module power generation efficiency, and the energy storage status, and clean the photovoltaic module according to the cleaning strategy.

2. The photovoltaic module cleaning method based on meteorological data according to claim 1, characterized in that: Obtaining the structure of the target photovoltaic module, and determining the sensor and online monitoring equipment for monitoring fault signals based on the structure, including: Obtaining the working principle and technical characteristics of the target photovoltaic module, and determining the structure of the target photovoltaic module based on the working principle and technical characteristics; Determine the key parameters that need to be monitored based on the structure of the target PV module, the working principle of the PV module, and the usage scenario; Obtain parameter types and parameter quantities of key parameters, and determine sensors based on the parameter types and parameter quantities; Obtain the sensor type and obtain the online monitoring device for monitoring fault signals based on the key parameters that need to be monitored.

3. The photovoltaic module cleaning method based on meteorological data according to claim 1, characterized in that: Build a data acquisition network to collect real-time operating data of the target photovoltaic panels based on sensors and online monitoring equipment that monitors fault signals, including: Obtain target data acquisition equipment based on target PV panels and working environment; Determine the data collection frequency and time point based on the target data collection equipment and the data coverage of the collection; Build a data collection device network based on wireless mode according to the data collection frequency and data collection time point; The real-time operating data of the target photovoltaic panel is collected based on the data acquisition network, sensors and online monitoring equipment that monitors fault signals.

4. The photovoltaic module cleaning method based on meteorological data according to claim 1, characterized in that: Analyzing the real-time operating data according to a real-time data processing algorithm, identifying power generation anomalies according to the analysis results, and determining a photovoltaic module failure mode based on the power generation anomaly based on a deep learning model, including: Analyzing the real-time running data according to a real-time data processing algorithm, and determining the indicators of cluster centroid distance and average distance within the cluster according to the analysis results; determining abnormal operation data according to the indicator, obtaining an abnormality type of the abnormal operation data, and identifying power generation abnormality according to the abnormality type; Acquire deep learning models based on different model architectures and parameter configurations according to actual application scenarios and the characteristics of abnormal operation data; A photovoltaic component failure mode is determined based on a deep learning model according to the power generation anomaly.

5. The photovoltaic module cleaning method based on meteorological data according to claim 1, characterized in that: Obtain weather forecast information for the next 24 hours, and determine the impact of weather conditions on photovoltaic module power generation efficiency based on the module power generation performance model according to the weather forecast information, including: Obtain weather forecast information for the next 24 hours based on the Meteorological Bureau data source; Extracting features related to photovoltaic module power generation efficiency based on weather forecast information using a machine learning algorithm; Build a module power generation performance model based on historical meteorological data and characteristics related to PV module power generation efficiency, and evaluate the model based on evaluation indicators; Determine the power generation efficiency of the target PV modules under different weather conditions based on the evaluated model and the weather forecast information for the next 24 hours; The influence of weather conditions on the power generation efficiency of the photovoltaic module is determined based on the power generation efficiency.

6. The photovoltaic module cleaning method based on meteorological data according to claim 1, characterized in that: The energy storage balance is determined based on the real-time status of the photovoltaic energy storage system. The expected photovoltaic conversion efficiency and post-cleaning gain are determined based on the expected power generation, including: monitoring the status of the photovoltaic energy storage system in real time according to the control system, obtaining the current capacity of the photovoltaic energy storage system according to the real-time status, and determining the energy storage balance according to the current capacity; Determine the expected power generation based on the efficiency of the photovoltaic panels according to the energy storage balance, and determine the expected photovoltaic conversion efficiency based on the expected power generation and weather conditions; Obtain the efficiency of the photovoltaic cell and determine the gain after cleaning in combination with the expected photoelectric conversion efficiency.

7. The photovoltaic module cleaning method based on meteorological data according to claim 1, characterized in that: A cleaning strategy is formulated based on the photovoltaic module failure mode, the impact of weather conditions on the photovoltaic module power generation efficiency, and the energy storage status, and the photovoltaic module is cleaned according to the cleaning strategy, including: locating the fault and determining the cause of the fault according to the photovoltaic module failure mode; Determine the degree of impact based on the impact of weather conditions on the power generation efficiency of photovoltaic modules; Cleaning information is determined according to the cause of the fault, the degree of impact, and the energy storage status, a cleaning strategy is formulated according to the cleaning information, and the photovoltaic components are cleaned according to the cleaning strategy.

8. The photovoltaic module cleaning method based on meteorological data according to claim 7, characterized in that: Cleaning of photovoltaic modules is achieved according to the cleaning strategy, including: Determine the stain type and stain area, determine the stain step characteristics based on the stain type and stain area, and determine the surface coverage damage characteristics of the photovoltaic module based on the stain distribution characteristics; Determine the three-dimensional characteristic matrix of the surface grain size of the photovoltaic module according to the surface coverage damage characteristics of the photovoltaic module; Determining a cleaning amplitude characteristic matrix for the surface of the photovoltaic module based on a three-dimensional characteristic matrix of particle size and a three-dimensional matrix of standard cleanliness of the surface of the photovoltaic module; Obtaining dust drift information in the operating environment of the photovoltaic module, and determining the daily dust deposition amount variable and the weekly dust deposition amount variable of the photovoltaic module based on the dust drift information; Calculate the increasing index between the daily dust deposition variable and the weekly dust deposition variable, and determine the power generation efficiency attenuation rate of the photovoltaic module based on the increasing index and the cleaning amplitude characteristic matrix of the photovoltaic module surface; Collecting operating parameter information of photovoltaic modules, and dividing the photovoltaic modules into different regional performance matrices according to the operating parameter information and preset performance classification standards; Based on the power generation efficiency attenuation rate of photovoltaic modules and the regional performance matrix, multiple effective cleaning frameworks and multiple cleaning time points are planned without affecting power generation efficiency; Determine multiple effective cleaning frameworks and multiple cleaning time points under the cleaning strategy for multiple cleaning yields; The target cleaning time point with the highest cleaning yield and the target effective cleaning frame are selected as the optimal cleaning time point and the optimal cleaning position area, and the optimal cleaning position area of the photovoltaic module is cleaned at the optimal cleaning time point based on the cleaning strategy.

Images