Photovoltaic power generation efficiency evaluation method, device, equipment and storage medium

Abstract

The invention discloses a photovoltaic power generation efficiency evaluation method and device, equipment and a storage medium, and relates to the technical field of renewable energy sources, and the method comprises the steps: obtaining multi-source photovoltaic power generation data in real time, and the multi-source photovoltaic power generation data comprises electric meter data, panoramic image data, thermal imaging data, irradiance data and environment temperature data; performing image analysis on the panoramic image data and the thermal imaging data to obtain an image analysis result, and determining an abnormal photovoltaic panel according to an image recognition result; calculating the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result; acquiring historical power generation efficiency, and performing time sequence analysis according to the historical power generation efficiency and the real-time power generation efficiency to obtain an efficiency analysis result; and generating an efficiency evaluation report according to the efficiency analysis result and the abnormal photovoltaic panel. According to the invention, the power generation efficiency of the photovoltaic power station can be accurately evaluated.

Description

Technical Field

[0001] The present application relates to the field of renewable energy technology, and in particular to a photovoltaic power generation efficiency evaluation method, device, equipment and storage medium. Background Art

[0002] In the current photovoltaic power generation field, there are certain limitations in the evaluation of the power generation efficiency of photovoltaic power plants. Traditional evaluation methods usually rely on inverter data or meter readings as the only data source. Although these data can reflect the overall power generation situation, they lack detailed component-level information. Relying only on inverter data and meter readings, it is impossible to obtain the specific performance data of a single photovoltaic panel or component, and thus it is impossible to identify local problems, such as failure or performance degradation of individual photovoltaic panels, resulting in inaccurate overall evaluation results. In other words, the lack of detailed component-level data limits the accuracy of the evaluation of the power generation efficiency of photovoltaic power plants.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a photovoltaic power generation efficiency evaluation method, device, equipment and storage medium, aiming to solve the technical problem that the evaluation results of photovoltaic power station power generation efficiency are not accurate enough.

[0005] To achieve the above purpose, the present application proposes a photovoltaic power generation efficiency evaluation method, which includes: Acquire multi-source photovoltaic power generation data in real time, wherein the multi-source photovoltaic power generation data includes electric meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; Performing image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results, and determining abnormal photovoltaic panels according to the image recognition results; Calculating the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result; Acquire historical power generation efficiency, perform time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, and obtain efficiency analysis results; An efficiency evaluation report is generated according to the efficiency analysis result and the abnormal photovoltaic panel.

[0006] In one embodiment, the step of performing image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results includes: Performing target detection on the photovoltaic panels in the panoramic image data to determine each photovoltaic panel in the panoramic image data and the model of each photovoltaic panel; Performing a thermal map analysis on the thermal imaging data to generate a temperature distribution map of the photovoltaic power station, and determining a photovoltaic panel temperature range of each photovoltaic panel according to each photovoltaic panel in the panoramic image data and the temperature distribution map of the photovoltaic power station; Calculating the total number of the photovoltaic panels, and calculating the total area of ​​the photovoltaic panels of the photovoltaic power station according to the total number and models of the photovoltaic panels; The photovoltaic panel temperature range and the photovoltaic panel total area are taken as image analysis results.

[0007] In one embodiment, the step of determining abnormal photovoltaic panels according to the image analysis results includes: Determine a first photovoltaic panel with abnormal temperature according to the photovoltaic panel temperature range of each photovoltaic panel; detecting the surface condition of each photovoltaic panel in the panoramic image data, and determining a photovoltaic panel with an abnormal surface condition as a second photovoltaic panel; The first photovoltaic panel and the second photovoltaic panel are determined to be abnormal photovoltaic panels.

[0008] In one embodiment, the step of calculating the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result includes: Preprocessing the electric meter data to obtain the actual power generation of the photovoltaic power station; Calculating the photoelectric conversion efficiency of the photovoltaic power station based on the actual power generation, the irradiance data and the total area of ​​the photovoltaic panels; Calculating theoretical power generation based on the irradiance data, the total area of ​​the photovoltaic panels, the photoelectric conversion efficiency, and the ambient temperature data; The real-time power generation efficiency of the photovoltaic power station is determined according to the actual power generation and the theoretical power generation.

[0009] In one embodiment, before the step of generating an efficiency evaluation report according to the efficiency analysis result and the abnormal photovoltaic panel, the step further includes: Acquire the voltage value, current value and temperature value of each photovoltaic panel in real time, and calculate the real-time power generation of each photovoltaic panel according to the voltage value and the current value; Performing clustering processing on each photovoltaic panel according to the real-time power generation, the temperature value of the photovoltaic panel, and the irradiance data of each photovoltaic panel to obtain a clustering result for each photovoltaic panel; The significant features of each photovoltaic panel are identified according to the clustering results of each photovoltaic panel, and an efficiency evaluation report is generated according to the significant features of each photovoltaic panel.

[0010] In one embodiment, after the step of calculating the real-time power generation of each photovoltaic panel according to the voltage value and the current value, the method further includes: Determine current performance data according to the real-time power generation of each photovoltaic panel and the temperature value of the photovoltaic panel; Acquire historical performance data of each of the photovoltaic panels, and calculate a historical performance deviation value based on the historical performance data and the current performance data; Determining adjacent photovoltaic panels of each photovoltaic panel, and calculating adjacent performance deviation values ​​according to current performance data of the photovoltaic panel and current performance data of the adjacent photovoltaic panels; Obtaining a preset standard temperature, and calculating the degree of temperature abnormality according to current performance data of the photovoltaic panel and the preset standard temperature; Performing a weighted summation of the historical performance deviation value, the adjacent performance deviation value, and the temperature anomaly degree to obtain an anomaly score; An efficiency evaluation report is generated according to the abnormality score of each photovoltaic panel.

[0011] In one embodiment, the step of performing time series analysis according to the historical power generation efficiency and the real-time power generation efficiency to obtain an efficiency analysis result includes: Inputting the historical power generation efficiency into a preset prediction model to obtain a predicted efficiency output by the model; Comparing the predicted efficiency with the real-time power generation efficiency to determine whether the real-time power generation efficiency is within a preset deviation range of the predicted efficiency; If the real-time power generation efficiency is outside the preset deviation range of the predicted efficiency, the real-time power generation efficiency is determined to be abnormal power generation efficiency, and an efficiency analysis result is determined based on the real-time power generation efficiency being abnormal power generation efficiency.

[0012] In addition, to achieve the above purpose, the present application also proposes a photovoltaic power generation efficiency evaluation device, the photovoltaic power generation efficiency evaluation device comprising: A data acquisition module, used to acquire multi-source photovoltaic power generation data in real time, wherein the multi-source photovoltaic power generation data includes electric meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; An image analysis module, used to perform image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results, and determine abnormal photovoltaic panels based on the image recognition results; An efficiency calculation module, used to calculate the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result; A time analysis module, used to obtain historical power generation efficiency, perform time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, and obtain efficiency analysis results; A report generation module is used to generate an efficiency evaluation report based on the efficiency analysis result and the abnormal photovoltaic panel.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a photovoltaic power generation efficiency evaluation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the photovoltaic power generation efficiency evaluation method as described above.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the photovoltaic power generation efficiency evaluation method described above are implemented.

[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the photovoltaic power generation efficiency evaluation method as described above are implemented.

[0016] The present application acquires various types of multi-source photovoltaic power generation data in real time, including meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; performs image analysis on the panoramic image data and thermal imaging data to obtain image analysis results, and determines abnormal photovoltaic panels based on the image recognition results, and automatically detects abnormal conditions of photovoltaic panels through image analysis technology, including surface dirt, cracks, heat, etc., so as to quickly locate problematic photovoltaic panels; calculates the real-time power generation efficiency of the photovoltaic power station based on the multi-source photovoltaic power generation data and image analysis results, calculates the power generation efficiency of the photovoltaic power station in real time, and performs performance evaluation immediately; obtains historical power generation efficiency, performs time series analysis based on historical power generation efficiency and real-time power generation efficiency, obtains efficiency analysis results, identifies changing trends and abnormal fluctuations in power generation efficiency, and provides long-term performance evaluation and prediction; generates an efficiency evaluation report based on the efficiency analysis results and abnormal photovoltaic panels, including the overall performance of the photovoltaic power station, the location and type of abnormal photovoltaic panels, efficiency change trends and improvement suggestions. This application can collect various types of data in real time through multi-sensor collaborative processing, and provide instant performance evaluation of photovoltaic power stations. It not only improves the management efficiency of photovoltaic power stations, but also realizes real-time and accurate evaluation of the power generation efficiency of photovoltaic power stations, which helps to improve the overall performance and maintenance efficiency of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of a process flow provided for Embodiment 1 of the photovoltaic power generation efficiency evaluation method of the present application; Figure 2 A phase flow chart of the photovoltaic power generation efficiency evaluation method provided in Example 1 of the present application; Figure 3 A schematic diagram of a brief process of a photovoltaic power generation efficiency evaluation method provided in Example 1 of the present application; Figure 4 This is a schematic diagram of the module structure of the photovoltaic power generation efficiency evaluation device according to the embodiment of the present application; Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the photovoltaic power generation efficiency evaluation method in the embodiment of the present application.

[0020] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0022] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0023] Based on this, the present application embodiment provides a photovoltaic power generation efficiency evaluation method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the photovoltaic power generation efficiency evaluation method of the present application.

[0024] In this embodiment, the photovoltaic power generation efficiency evaluation method includes steps S10 to S50: Step S10, acquiring multi-source photovoltaic power generation data in real time, wherein the multi-source photovoltaic power generation data includes electric meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data.

[0025] In a feasible implementation, step S10 may include steps S11 to S13: Step S11, establishing a communication connection with a handheld infrared device, and acquiring the electric meter data collected by the handheld infrared device based on the communication connection.

[0026] It should be noted that the handheld infrared device is used to collect real-time power generation data during the detection of photovoltaic power stations. The handheld infrared device uses a high-precision, low-power infrared sensor, which can accurately capture the data display of the meter, support the meter data collection of the remote control communication 645 protocol, and can collect key parameters including the combined forward active total power.

[0027] Step S12, obtaining panoramic image data and thermal imaging data of the photovoltaic power station collected by the cruising drone.

[0028] It should be noted that the cruise drone can collect panoramic images and thermal imaging data of photovoltaic power stations from a high-altitude perspective. The main body of the drone adopts an industrial-grade drone with high endurance and strong wind resistance. It needs to have a high-definition camera with a resolution of no less than 4K, support optical zoom, and be equipped with a thermal imaging device with a temperature measurement accuracy of ±2°C and a resolution of no less than 640×480. It has an RTK module and can provide centimeter-level positioning accuracy to ensure the accuracy of the flight trajectory. The drone supports preset flight paths, can realize automatic inspections, supports multi-spectral imaging, and can identify tiny defects in photovoltaic panels.

[0029] Step S13, obtaining irradiance data and ambient temperature data collected by the irradiator.

[0030] It should be noted that the irradiance meter can measure irradiance data and temperature values ​​at the same time. The high-precision irradiance sensor has a measurement range of 0-2000W / m² and an accuracy of ≤±2%. The temperature sensor can measure the ambient temperature and the temperature of the photovoltaic panel backplane. It supports wired and wireless communication methods, can monitor solar irradiance, ambient temperature and photovoltaic panel temperature in real time, supports multi-point layout, and can capture the irradiance distribution differences of large power stations.

[0031] Step S20, performing image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results, and determining abnormal photovoltaic panels based on the image recognition results.

[0032] It should be noted that for panoramic image data, image analysis may include: edge detection, using the Canny edge detection algorithm or the Sobel operator to extract the edge information of the photovoltaic panel; color segmentation, using color space (such as HSV) to perform color segmentation to distinguish the photovoltaic panel from other backgrounds; morphological operations, using open and close operations to remove small noise areas and retain the main photovoltaic panel outlines. For thermal imaging data, image analysis may include: temperature distribution, extracting the temperature value of each pixel and generating a temperature distribution map; hot spot detection, identifying areas with abnormally high temperatures, which may be fault points; temperature gradient, calculating the temperature gradient, and identifying areas with drastic temperature changes.

[0033] In a feasible implementation, step S20 may include steps A10 to A40: Step A10, performing target detection on the photovoltaic panels in the panoramic image data, and determining each photovoltaic panel and the model of each photovoltaic panel in the panoramic image data.

[0034] It should be noted that object detection uses machine learning or deep learning models to locate and classify objects in images. Specifically, for photovoltaic panel detection, you can use region-based convolutional neural networks (R-CNN), single-stage detectors (such as YOLO (You Only Look Once) or SSD (Single Shot MultiBox Detector), which directly predict object bounding boxes and class probabilities and are faster). Or instance segmentation (if you need to segment the edges of photovoltaic panels more accurately, you can use models such as Mask R-CNN).

[0035] Once the location of the photovoltaic panels is detected, the next step is to identify the specific model of each photovoltaic panel. If reference images of photovoltaic panels of different models are known, a template matching algorithm can be used, or a specially trained classifier, such as CNN, can be used to identify the model based on the visual features of the photovoltaic panel.

[0036] Step A20, performing a thermal map analysis on the thermal imaging data to generate a temperature distribution map of the photovoltaic power station, and determining the photovoltaic panel temperature range of each photovoltaic panel according to each photovoltaic panel in the panoramic image data and the temperature distribution map of the photovoltaic power station.

[0037] It should be noted that the temperature distribution map is generated by thermal imaging data to intuitively display the temperature distribution of the photovoltaic power station. The specific steps may include: converting the pixel values ​​in the thermal imaging data into actual temperature values, using color coding to represent different temperature ranges, and generating a color temperature distribution map. Then, using the photovoltaic panel position information detected in the panoramic image data, for each photovoltaic panel, determine the temperature range or other statistics within its coverage area. Among them, in addition to the photovoltaic panel temperature range, the present application can also set a temperature sensor for each photovoltaic panel separately to detect the temperature value of each photovoltaic panel to obtain temperature data that is more accurate than the photovoltaic panel temperature range.

[0038] Step A30, calculating the total number of photovoltaic panels, and calculating the total area of ​​photovoltaic panels of the photovoltaic power station according to the total number and models of photovoltaic panels.

[0039] It should be noted that computer vision technology (such as deep learning-based target detection algorithms) can be used to automatically detect and count each photovoltaic panel from the panoramic image data. Next, it is necessary to know the area corresponding to each photovoltaic panel model. Using the total number of photovoltaic panels and the area of ​​each photovoltaic panel, the total area of ​​the photovoltaic panels in the photovoltaic power station can be calculated, usually by multiplying the area of ​​each photovoltaic panel by its number and then adding them up.

[0040] Step A40, taking the photovoltaic panel temperature range and the photovoltaic panel total area as image analysis results.

[0041] This implementation method can not only accurately detect and identify the location and model of each photovoltaic panel through comprehensive analysis of panoramic image data and thermal imaging data, but also generate detailed temperature distribution maps and calculate the total number and total area of ​​photovoltaic panels. Finally, this information is integrated into image analysis results to provide reliable data support for subsequent power generation efficiency evaluation.

[0042] In a feasible implementation manner, step S30 may further include steps A50 to A80: Step A50: determining a first photovoltaic panel with abnormal temperature according to the photovoltaic panel temperature range of each photovoltaic panel.

[0043] It should be noted that before performing temperature anomaly detection, reasonable temperature thresholds need to be set. These thresholds can be determined based on industry standards, historical data, or expert experience. Temperature thresholds can include high temperature thresholds, low temperature thresholds, and temperature difference thresholds.

[0044] For each photovoltaic panel, its temperature range needs to be determined, and based on the set temperature threshold, it is determined whether each photovoltaic panel has a temperature anomaly. Specifically, if the temperature of the photovoltaic panel exceeds the set high temperature threshold or low temperature threshold, or the temperature difference exceeds the temperature difference threshold, it is marked as the first photovoltaic panel with temperature anomaly.

[0045] Step A60, detecting the surface condition of each photovoltaic panel in the panoramic image data, and determining the photovoltaic panel with abnormal surface condition as the second photovoltaic panel.

[0046] It should be noted that in order to detect the surface condition of photovoltaic panels, features need to be extracted from images. These features may include edges, textures, colors, etc. In order to detect the surface condition of photovoltaic panels, features need to be extracted from images. These features may include edges, textures, colors, etc. Local binary patterns (LBP), gray-level co-occurrence matrix (GLCM) and other methods are used to analyze the texture of the surface of photovoltaic panels. Then, using the extracted features, anomaly detection algorithms are applied to identify anomalies on the surface of photovoltaic panels. For example, pre-trained convolutional neural network (CNN) models such as ResNet, VGG, etc. are used to classify photovoltaic panel images, identify anomalies, and use rule-based methods such as template matching, morphological operations, etc. to detect specific types of defects.

[0047] Step A70: determining the first photovoltaic panel and the second photovoltaic panel as abnormal photovoltaic panels.

[0048] This implementation achieves comprehensive identification of abnormal photovoltaic panels in a photovoltaic power station. It can not only accurately detect photovoltaic panels with abnormal temperatures, but also identify photovoltaic panels with abnormal surface conditions, and merge these two types of abnormal photovoltaic panels to form a final list of abnormal photovoltaic panels.

[0049] Step S30, calculating the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result.

[0050] In a feasible implementation, step S30 may include steps S31 to S34: Step S31, pre-processing the electric meter data to obtain the actual power generation of the photovoltaic power station.

[0051] It should be noted that the raw power generation data is read from the electricity meter or other data source, and data cleaning is performed on it, including removing outliers, missing values ​​and noise data, and converting units. The actual power generation is usually the total power generation in a certain period of time.

[0052] Step S32, calculating the photoelectric conversion efficiency of the photovoltaic power station based on the actual power generation, the irradiance data and the total area of ​​the photovoltaic panels.

[0053] It should be noted that the photoelectric conversion efficiency refers to the ratio of actual power generation to theoretical maximum power generation. The theoretical maximum power generation refers to the maximum amount of electricity that a photovoltaic power station can generate under ideal conditions. This value can be calculated using the following formula: Theoretical maximum power generation = irradiance × total area of ​​photovoltaic panels × conversion efficiency under standard test conditions.

[0054] The conversion efficiency under standard test conditions usually refers to the conversion efficiency of photovoltaic panels measured under standard test conditions (STC). STC conditions are usually defined as: temperature: 25°C, irradiance: 1000 W / m², air quality: AM1.5.

[0055] Step S33, calculating the theoretical power generation based on the irradiance data, the total area of ​​the photovoltaic panels, the photoelectric conversion efficiency, and the ambient temperature data.

[0056] The theoretical power generation Q_theoretical can be calculated by the following formula: Q_theoretical=∑(G_i*A*η*Δt_i*(1-β(T_i-T_STC))) where G_i is the irradiance in the i-th time period, A is the total area of ​​the photovoltaic panel, η is the photoelectric conversion efficiency, Δt_i is the time interval, β is the temperature coefficient, T_i is the actual temperature, and T_STC is the standard test condition temperature (usually 25°C).

[0057] It should be noted that the irradiance data is the solar irradiance data at the location of the photovoltaic power station, usually in watts per square meter (W / m²), the total area of ​​photovoltaic panels is the total area of ​​all photovoltaic panels in the photovoltaic power station, usually in square meters (m²), the photoelectric conversion efficiency is the photoelectric conversion efficiency obtained from step S32, and the ambient temperature data is the ambient temperature data at the location of the photovoltaic power station, usually in degrees Celsius (°C). The output power of the photovoltaic panel is affected by the temperature. Generally, an increase in temperature will cause the output power of the photovoltaic panel to decrease. Therefore, it is necessary to introduce a temperature correction coefficient (1-β(T_i-T_STC)) to adjust the calculation of the theoretical power generation, where the temperature coefficient represents the percentage of output power decrease for every 1°C increase in temperature (for example, -0.5% per degree).

[0058] Step S34: determining the real-time power generation efficiency of the photovoltaic power station according to the actual power generation and the theoretical power generation.

[0059] It should be noted that the power generation efficiency calculation formula is: real-time power generation efficiency = theoretical power generation / actual power generation. Considering the influence of factors such as dust and shadows, a correction factor k can be introduced, and the value of k is dynamically adjusted through historical data analysis and machine learning algorithms.

[0060] This implementation effectively calculates the actual power generation, photoelectric conversion efficiency, theoretical power generation and real-time power generation efficiency of the photovoltaic power station, ensuring accurate evaluation of the performance of the photovoltaic power station.

[0061] Step S40, obtaining historical power generation efficiency, performing time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, and obtaining efficiency analysis results.

[0062] In a feasible implementation, step S40 may include steps S41 to S43: Step S41, inputting the historical power generation efficiency into a preset prediction model to obtain the predicted efficiency output by the model.

[0063] It should be noted that, first of all, it is necessary to collect and prepare historical data for training the prediction model, including the actual power generation of the photovoltaic power station in the past period of time, and the theoretical power generation calculated based on environmental conditions such as irradiance (solar radiation intensity), temperature, humidity, etc. Then select a suitable prediction model, such as a time series model, a machine learning model, or a deep learning model, and use historical data to train the selected model. Use the trained model to predict the data of the current time period to obtain the predicted power generation efficiency.

[0064] Step S42: Compare the predicted efficiency with the real-time power generation efficiency to determine whether the real-time power generation efficiency is within a preset deviation range of the predicted efficiency.

[0065] It should be noted that, first, a reasonable deviation range is set. This range can be determined based on the empirical value of historical data or industry standards. For example, if historical data shows that the actual power generation efficiency usually fluctuates within ±5% of the predicted value, then ±5% can be set as the preset deviation range. Calculate the deviation between the real-time power generation efficiency and the predicted efficiency, and determine whether the real-time power generation efficiency is within a reasonable range based on the preset deviation range. If the deviation is less than or equal to the preset deviation range, the real-time power generation efficiency is considered normal; otherwise, the real-time power generation efficiency is considered abnormal.

[0066] Step S43: if the real-time power generation efficiency is outside the preset deviation range of the predicted efficiency, the real-time power generation efficiency is determined to be abnormal power generation efficiency, and an efficiency analysis result is determined based on the real-time power generation efficiency being abnormal power generation efficiency.

[0067] It should be noted that, in addition to the real-time power generation efficiency and predicted efficiency, the efficiency analysis results may also include information such as the deviation between the real-time power generation efficiency and the predicted efficiency, whether it exceeds the preset deviation range, the cause of the abnormality, and suggested measures for the abnormal cause.

[0068] This implementation ensures accurate evaluation of the real-time power generation efficiency of the photovoltaic power station, and provides important performance indicators and anomaly detection mechanisms, which can effectively determine whether the real-time power generation efficiency of the photovoltaic power station is abnormal based on historical power generation efficiency and real-time power generation efficiency.

[0069] Step S50, generating an efficiency evaluation report according to the efficiency analysis results and abnormal photovoltaic panels.

[0070] For example, Figure 2 A phase flow chart is provided, such as Figure 2 As shown, the evaluation system provided in this embodiment includes five modules: handheld infrared data collection, drone cruise analysis, image recognition, irradiance measurement, data processing and evaluation, and five execution stages: data collection stage, data transmission stage, data processing stage, efficiency evaluation stage and result analysis and report generation stage. During the data collection phase, users hold infrared meters to continuously collect meter data and record initial values, usually in a 5-minute cycle, for a total of 30 minutes. The drone cruises overhead to inspect the photovoltaic station along a preset path, collecting panoramic images and thermal imaging data, i.e., visible light and invisible light photos. The photos are processed at the same time to calculate the installed capacity of the photovoltaic power station, and the irradiance meter records the solar irradiance and temperature data in real time. During the data transmission phase, all collected data are transmitted to the cloud platform in real time through a secure channel, and a data integrity check is performed to ensure that all necessary data has been collected. During the data processing phase, images collected by drones are processed through image recognition to identify ground station data, the number of photovoltaic panels and abnormal conditions, and all collected data are cleaned and preprocessed. During the efficiency evaluation phase, the actual power generation efficiency is calculated based on the processed data, the actual efficiency is compared with the theoretical efficiency, and the efficiency abnormality area is identified. During the result analysis and report generation phase, the causes of efficiency abnormalities are analyzed, which may include equipment failures, environmental factors, etc., and a comprehensive report containing efficiency evaluation results, abnormality analysis and optimization suggestions is generated.

[0071] This embodiment acquires various types of multi-source photovoltaic power generation data in real time, including meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; performs image analysis on the panoramic image data and thermal imaging data to obtain image analysis results, and determines abnormal photovoltaic panels based on the image recognition results. Through image analysis technology, abnormal conditions of photovoltaic panels are automatically detected, including surface dirt, cracks, heat, etc., so as to quickly locate problematic photovoltaic panels; calculates the real-time power generation efficiency of the photovoltaic power station based on the multi-source photovoltaic power generation data and the image analysis results, calculates the power generation efficiency of the photovoltaic power station in real time, and performs performance evaluation immediately; obtains historical power generation efficiency, performs time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, obtains efficiency analysis results, identifies changing trends and abnormal fluctuations in power generation efficiency, and provides long-term performance evaluation and prediction; generates an efficiency evaluation report based on the efficiency analysis results and abnormal photovoltaic panels, including the overall performance of the photovoltaic power station, the location and type of abnormal photovoltaic panels, efficiency change trends and improvement suggestions. This embodiment can collect various types of data in real time through multi-sensor collaborative processing, and provide instant performance evaluation of the photovoltaic power station. It not only improves the management efficiency of the photovoltaic power station, but also realizes real-time and accurate evaluation of the power generation efficiency of the photovoltaic power station, which helps to improve the overall performance and maintenance efficiency of the photovoltaic power station.

[0072] For example, in order to help understand the implementation process of the photovoltaic power generation efficiency evaluation method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief schematic diagram of a photovoltaic power generation efficiency evaluation method is provided, specifically: The power generation efficiency evaluation system proposed in this embodiment includes the following five modules: handheld infrared data collection, drone cruise analysis, image recognition, irradiance measurement, data processing and evaluation. The five modules are executed in parallel, and the modules are connected and exchange data through the data bus and the software system supporting this embodiment to form a complete information collection, transmission, processing and analysis system. Among them, 1-6 represents 6 steps, 1 is the handheld infrared device collecting meter data on the meter, 2 is the drone cruise thermal imaging analysis of the photovoltaic module, 3 is the image recognition of the photovoltaic module, 4 is the irradiator for irradiance measurement, 5 is the cloud platform for data processing and evaluation, and 6 is the report generation.

[0073] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. On this basis, before step S50, the photovoltaic power generation efficiency evaluation method further includes steps B10 to B30: Step B10, obtaining the voltage value, current value and temperature value of each photovoltaic panel in real time, and calculating the real-time power generation of each photovoltaic panel according to the voltage value and the current value.

[0074] It should be noted that voltage sensors and current sensors are installed on each photovoltaic panel to monitor voltage and current in real time. Data acquisition systems (such as SCADA systems, data loggers, etc.) collect data from sensors regularly or continuously and transmit the data to a cloud platform or data center via wired or wireless means. The real-time power generation of each photovoltaic panel can be calculated using the formula P=IV, where P is the real-time power generation, V is the voltage, and I is the current.

[0075] Step B20, clustering each photovoltaic panel according to the real-time power generation, the photovoltaic panel temperature value, and the irradiance data of each photovoltaic panel to obtain a clustering result for each photovoltaic panel.

[0076] It should be noted that the photovoltaic panel temperature range here can be replaced by the photovoltaic panel temperature measured by the temperature sensor arranged in each photovoltaic panel, which is more accurate than the photovoltaic panel temperature range. This application uses real-time power generation, photovoltaic panel temperature range, and irradiance data as clustering features, selects a clustering algorithm, and applies the selected clustering algorithm to cluster the data. According to the clustering results, the cluster category to which each photovoltaic panel belongs can be determined. Among them, the fineness of the clustering can be controlled by controlling the number of clusters.

[0077] Step B30, identifying significant features of each photovoltaic panel according to the clustering results of each photovoltaic panel, and generating an efficiency evaluation report according to the significant features of each photovoltaic panel.

[0078] In a feasible implementation manner, after step B10, steps C10 to C60 may also be included: Step C10, determining current performance data according to the real-time power generation of each photovoltaic panel and the temperature value of the photovoltaic panel.

[0079] It should be noted that the current performance data is a combination of real-time power generation and photovoltaic panel temperature values.

[0080] Step C20 obtains historical performance data of each photovoltaic panel, and calculates a historical performance deviation value based on the historical performance data and the current performance data.

[0081] The historical performance deviation values ​​include the historical performance deviation values ​​of the real-time power generation and the historical performance deviation values ​​of the photovoltaic panel temperature value.

[0082] Step C30, determining the adjacent photovoltaic panels of each photovoltaic panel, and calculating the adjacent performance deviation value according to the current performance data of the photovoltaic panel and the current performance data of the adjacent photovoltaic panels.

[0083] It should be noted that in the previous image recognition, each photovoltaic panel has been identified from the panoramic image data, so the adjacent photovoltaic panels of each photovoltaic panel can be directly determined, and the adjacent performance deviation values ​​also include the adjacent performance deviation values ​​of the real-time power generation and the adjacent performance deviation values ​​of the photovoltaic panel temperature value.

[0084] Step C40, obtaining a preset standard temperature, and calculating the degree of temperature abnormality according to the current performance data of the photovoltaic panel and the preset standard temperature.

[0085] The temperature deviation between the photovoltaic panel temperature value in the current performance data and the preset standard temperature is calculated, and the degree of temperature anomaly is determined based on the temperature deviation. The degree of temperature anomaly can be directly the absolute temperature deviation, or the ratio of the temperature deviation to the standard temperature.

[0086] Step C50: performing weighted summation on the historical performance deviation value, the adjacent performance deviation value, and the temperature anomaly degree to obtain an anomaly score.

[0087] It should be noted that, based on actual conditions and experience, the weights of historical performance deviation values, adjacent performance deviation values ​​and the degree of temperature anomaly are defined, and the data of historical performance deviation values, adjacent performance deviation values ​​and the degree of temperature anomaly are merged into one data set.

[0088] Step C60, generating an efficiency evaluation report according to the abnormality score of each photovoltaic panel.

[0089] This embodiment conducts a more in-depth analysis of the performance of photovoltaic panels. It evaluates the performance of each photovoltaic panel by combining real-time data, historical data, and data from adjacent photovoltaic panels, and generates an efficiency evaluation report, ensuring a comprehensive evaluation of the performance of each photovoltaic panel in the photovoltaic power station.

[0090] This embodiment monitors the voltage and current values ​​of each photovoltaic panel in real time, calculates its real-time power generation, clusters the photovoltaic panels based on these data, and finally generates anomaly scores and efficiency evaluation reports based on the clustering results. It can effectively monitor, cluster and score anomalies of each photovoltaic panel in a photovoltaic power station in real time, thereby generating a detailed efficiency evaluation report, ensuring a comprehensive evaluation of the performance of each photovoltaic panel in the photovoltaic power station, and providing important performance indicators and anomaly detection mechanisms.

[0091] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the photovoltaic power generation efficiency evaluation method of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0092] This application also provides a photovoltaic power generation efficiency evaluation device, please refer to Figure 4 , the photovoltaic power generation efficiency evaluation device comprises: A data acquisition module 10 is used to acquire multi-source photovoltaic power generation data in real time, wherein the multi-source photovoltaic power generation data includes electric meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; An image analysis module 20 is used to perform image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results, and determine abnormal photovoltaic panels according to the image recognition results; An efficiency calculation module 30, used to calculate the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result; A time analysis module 40 is used to obtain historical power generation efficiency, perform time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, and obtain an efficiency analysis result; The report generating module 50 is used to generate an efficiency evaluation report according to the efficiency analysis result and the abnormal photovoltaic panel.

[0093] The photovoltaic power generation efficiency evaluation device provided by the present application adopts the photovoltaic power generation efficiency evaluation method in the above embodiment, which can solve the technical problem that the evaluation result of the photovoltaic power generation efficiency is not accurate enough. Compared with the prior art, the beneficial effects of the photovoltaic power generation efficiency evaluation device provided by the present application are the same as the beneficial effects of the photovoltaic power generation efficiency evaluation method provided by the above embodiment, and the other technical features in the photovoltaic power generation efficiency evaluation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0094] The present application provides a photovoltaic power generation efficiency evaluation device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the photovoltaic power generation efficiency evaluation method in the above-mentioned embodiment one.

[0095] Reference below Figure 5, which shows a schematic diagram of the structure of a photovoltaic power generation efficiency evaluation device suitable for implementing the embodiment of the present application. The photovoltaic power generation efficiency evaluation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The photovoltaic power generation efficiency evaluation device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0096] like Figure 5 As shown, the photovoltaic power generation efficiency evaluation device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the photovoltaic power generation efficiency evaluation device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the photovoltaic power generation efficiency evaluation device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a photovoltaic power generation efficiency evaluation device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0097] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0098] The photovoltaic power generation efficiency evaluation device provided by the present application adopts the photovoltaic power generation efficiency evaluation method in the above embodiment, which can solve the technical problem that the evaluation result of the power generation efficiency of the photovoltaic power station is not accurate enough. Compared with the prior art, the beneficial effects of the photovoltaic power generation efficiency evaluation device provided by the present application are the same as the beneficial effects of the photovoltaic power generation efficiency evaluation method provided by the above embodiment, and the other technical features in the photovoltaic power generation efficiency evaluation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0099] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0100] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0101] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the photovoltaic power generation efficiency evaluation method in the above-mentioned embodiment.

[0102] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned photovoltaic power generation efficiency evaluation method, and can solve the technical problem that the evaluation results of photovoltaic power generation efficiency are not accurate enough. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the photovoltaic power generation efficiency evaluation method provided in the above-mentioned embodiment, and will not be repeated here.

[0103] The present application also provides a computer program product, including a computer program, which implements the steps of the photovoltaic power generation efficiency evaluation method as described above when executed by a processor.

[0104] The computer program product provided by this application can solve the technical problem that the evaluation results of photovoltaic power station power generation efficiency are not accurate enough. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the photovoltaic power generation efficiency evaluation method provided by the above embodiment, which will not be repeated here.

[0105] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A photovoltaic power generation efficiency evaluation method, characterized in that: The photovoltaic power generation efficiency evaluation method comprises: Acquire multi-source photovoltaic power generation data in real time, wherein the multi-source photovoltaic power generation data includes electric meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; Performing image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results, and determining abnormal photovoltaic panels according to the image recognition results; Calculating the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result; Acquire historical power generation efficiency, perform time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, and obtain efficiency analysis results; An efficiency evaluation report is generated according to the efficiency analysis result and the abnormal photovoltaic panel.

2. The photovoltaic power generation efficiency evaluation method according to claim 1, characterized in that: The step of performing image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results comprises: Performing target detection on the photovoltaic panels in the panoramic image data to determine each photovoltaic panel in the panoramic image data and the model of each photovoltaic panel; Performing a thermal map analysis on the thermal imaging data to generate a temperature distribution map of the photovoltaic power station, and determining a photovoltaic panel temperature range of each photovoltaic panel according to each photovoltaic panel in the panoramic image data and the temperature distribution map of the photovoltaic power station; Calculating the total number of the photovoltaic panels, and calculating the total area of ​​the photovoltaic panels of the photovoltaic power station according to the total number and models of the photovoltaic panels; The photovoltaic panel temperature range and the photovoltaic panel total area are taken as image analysis results.

3. The photovoltaic power generation efficiency evaluation method according to claim 2, characterized in that: The step of determining abnormal photovoltaic panels according to the image analysis results includes: Determine a first photovoltaic panel with abnormal temperature according to the photovoltaic panel temperature range of each photovoltaic panel; detecting the surface condition of each photovoltaic panel in the panoramic image data, and determining a photovoltaic panel with an abnormal surface condition as a second photovoltaic panel; The first photovoltaic panel and the second photovoltaic panel are determined to be abnormal photovoltaic panels.

4. The photovoltaic power generation efficiency evaluation method according to claim 2, characterized in that: The step of calculating the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result comprises: Preprocessing the electric meter data to obtain the actual power generation of the photovoltaic power station; Calculating the photoelectric conversion efficiency of the photovoltaic power station based on the actual power generation, the irradiance data and the total area of ​​the photovoltaic panels; Calculating theoretical power generation based on the irradiance data, the total area of ​​the photovoltaic panels, the photoelectric conversion efficiency, and the ambient temperature data; The real-time power generation efficiency of the photovoltaic power station is determined according to the actual power generation and the theoretical power generation.

5. The photovoltaic power generation efficiency evaluation method according to any one of claims 1 to 4, characterized in that: Before the step of generating an efficiency evaluation report according to the efficiency analysis result and the abnormal photovoltaic panel, the method further includes: Acquire the voltage value, current value and temperature value of each photovoltaic panel in real time, and calculate the real-time power generation of each photovoltaic panel according to the voltage value and the current value; Performing clustering processing on each photovoltaic panel according to the real-time power generation, the temperature value of the photovoltaic panel, and the irradiance data of each photovoltaic panel to obtain a clustering result for each photovoltaic panel; The significant features of each photovoltaic panel are identified according to the clustering results of each photovoltaic panel, and an efficiency evaluation report is generated according to the significant features of each photovoltaic panel.

6. The photovoltaic power generation efficiency evaluation method according to claim 5, characterized in that: After the step of calculating the real-time power generation of each photovoltaic panel according to the voltage value and the current value, the method further includes: Determine current performance data according to the real-time power generation of each photovoltaic panel and the temperature value of the photovoltaic panel; Acquire historical performance data of each of the photovoltaic panels, and calculate a historical performance deviation value based on the historical performance data and the current performance data; Determining adjacent photovoltaic panels of each photovoltaic panel, and calculating adjacent performance deviation values ​​according to current performance data of the photovoltaic panel and current performance data of the adjacent photovoltaic panels; Obtaining a preset standard temperature, and calculating the degree of temperature abnormality according to current performance data of the photovoltaic panel and the preset standard temperature; Performing a weighted summation of the historical performance deviation value, the adjacent performance deviation value, and the temperature anomaly degree to obtain an anomaly score; An efficiency evaluation report is generated according to the abnormality score of each photovoltaic panel.

7. The photovoltaic power generation efficiency evaluation method according to claim 1, characterized in that: The step of performing time series analysis according to the historical power generation efficiency and the real-time power generation efficiency to obtain an efficiency analysis result comprises: Inputting the historical power generation efficiency into a preset prediction model to obtain a predicted efficiency output by the model; Comparing the predicted efficiency with the real-time power generation efficiency to determine whether the real-time power generation efficiency is within a preset deviation range of the predicted efficiency; If the real-time power generation efficiency is outside the preset deviation range of the predicted efficiency, the real-time power generation efficiency is determined to be abnormal power generation efficiency, and an efficiency analysis result is determined based on the real-time power generation efficiency being abnormal power generation efficiency.

8. A photovoltaic power generation efficiency evaluation device, characterized in that: The photovoltaic power generation efficiency evaluation device comprises: A data acquisition module, used to acquire multi-source photovoltaic power generation data in real time, wherein the multi-source photovoltaic power generation data includes electric meter data, panoramic image data, thermal imaging data, irradiance data and ambient temperature data; An image analysis module, used to perform image analysis on the panoramic image data and the thermal imaging data to obtain image analysis results, and determine abnormal photovoltaic panels based on the image recognition results; An efficiency calculation module, used to calculate the real-time power generation efficiency of the photovoltaic power station according to the multi-source photovoltaic power generation data and the image analysis result; A time analysis module, used to obtain historical power generation efficiency, perform time series analysis based on the historical power generation efficiency and the real-time power generation efficiency, and obtain efficiency analysis results; A report generation module is used to generate an efficiency evaluation report based on the efficiency analysis result and the abnormal photovoltaic panel.

9. A photovoltaic power generation efficiency evaluation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the photovoltaic power generation efficiency evaluation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the photovoltaic power generation efficiency evaluation method according to any one of claims 1 to 7 are implemented.

Images