Photovoltaic cell management method based on Internet of Things

Abstract

The invention provides a photovoltaic cell management method based on the Internet of Things, and the method comprises the steps: collecting the key data of a photovoltaic cell, and uploading the key data to a cloud end; the key data is used for representing the working state of the photovoltaic cell; analyzing the key data, and regulating and controlling an input working point of the photovoltaic cell through a maximum power point tracking algorithm to enable the photovoltaic cell to maintain the maximum productivity efficiency so as to improve the key data; the input working point comprises an input current value and an input voltage value; and displaying the key data through a man-machine interaction page, and sending early warning information based on a preset path. According to the method, autonomous research and judgment of the algorithm can be carried out to maintain the photovoltaic cell in a good productivity efficiency state, data persistence storage is carried out, a user can track historical data conveniently, the user can be notified in time through a notification channel set by the user, and equipment safety is guaranteed.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and specifically to a photovoltaic battery management method based on the Internet of Things. Background Art

[0002] Photovoltaic power generation system is a system that uses the energy of solar photons to generate electricity. Its core component is photovoltaic cells, also known as solar panels, which are able to convert sunlight into electricity. Photovoltaic cells are usually made of semiconductor materials such as silicon. When sunlight shines on the surface of the cell, the photons excite the electrons in the semiconductor, causing the electrons to flow and generate electric current. This phenomenon is called the photovoltaic effect.

[0003] During the research process of conceiving and forming this application, the applicant has found at least the following problems: most photovoltaic battery management devices currently on the market can only achieve simple control of some functions. They are still insufficient in terms of intelligence, and there is also the problem of battery efficiency being wasted, resulting in a poor user experience. Summary of the invention

[0004] In order to alleviate the above problems, the present application provides a photovoltaic battery management method based on the Internet of Things, including: Collecting key data of photovoltaic cells and uploading the key data to the cloud; the key data is used to characterize the working status of the photovoltaic cells; Analyze the key data, and adjust the input working point of the photovoltaic cell through a maximum power point tracking algorithm so that the photovoltaic cell maintains maximum power generation efficiency to improve the key data; the input working point includes an input current value and an input voltage value; The key data is displayed through a human-computer interaction page, and early warning information is sent based on a preset path to ensure the safety of the photovoltaic cell.

[0005] Optionally, the key data includes input current and input voltage; and the step of analyzing the key data and regulating the input operating point of the photovoltaic cell by a maximum power point tracking algorithm so that the photovoltaic cell maintains maximum power generation efficiency to improve the key data includes: Initializing the maximum power point tracking algorithm, setting the input power of an initial working point as the input power of a cycle before initialization, the initial working point including an initial voltage value and an initial current value; Calculating the current input power of the photovoltaic cell according to the collected input current and input voltage; The current input power is compared with the input power of the previous cycle. If the current input power is higher, the operating point is adjusted in the same direction. If the power is lower, the operating point is continuously adjusted in the direction of changing the operating point.

[0006] Optionally, the key data includes environmental data; the maximum power point tracking algorithm includes a multi-peak tracking algorithm; The step of analyzing the key data and regulating the input working point of the photovoltaic cell by a maximum power point tracking algorithm so as to maintain the maximum power generation efficiency of the photovoltaic cell to improve the key data also includes: Using image processing technology to detect the position and size of the shadow on the photovoltaic cell, and based on the environmental data, identifying and tracking the local maximum power point based on a multi-peak tracking algorithm; Based on the dynamic sub-array division strategy, the photovoltaic panel is divided into multiple sub-arrays, each sub-array independently runs the multi-peak tracking algorithm, and monitors the surface temperature of the photovoltaic cell to perform hot spot monitoring processing to accurately predict and adjust the maximum power point.

[0007] Optionally, the step of using image processing technology to detect the position and size of the shadow on the photovoltaic cell includes: Based on a preset resolution and frame rate, an original surface image of the photovoltaic cell is collected, and the collected original surface image is adaptively preprocessed to improve image quality, thereby obtaining a preprocessed image; Based on the preprocessed image, applying image segmentation technology to distinguish shadow areas from non-shadow areas, and using a machine learning algorithm to classify shadow and non-shadow areas; Shadow features are extracted from the detected shadow area to determine the size and position of the shadow area and predict the impact of the shadow area on the performance of the photovoltaic cell.

[0008] Optionally, the step of adaptively preprocessing the acquired original surface image to improve image quality comprises: Based on the original surface image, a white balance adjustment is performed using a statistical method, and the image contrast is dynamically adjusted according to a histogram of the image to obtain an adjusted image; Using an algorithm based on Retinex theory to perform illumination correction and noise reduction on the adjusted image to obtain a noise-reduced image; An adaptive threshold is selected for the denoised image based on a local area method to perform image segmentation based on the threshold, and image enhancement is performed based on different illumination conditions to obtain a preprocessed image.

[0009] Optionally, the step of adaptively preprocessing the acquired original surface image to improve image quality further includes: The preprocessed image is converted from the RGB color space to the CIE Lab color space, the neutral color area in the image is found, the average values ​​of the R, G, and B components of the entire image are calculated, and normalization is performed to obtain a color correction gain to correct the color cast in the preprocessed image.

[0010] According to the result of white balance adjustment, the color of the whole image is adjusted to achieve color correction; The rectified image is converted back from Lab to RGB color space to optimize the pre-processed image.

[0011] Optionally, the step of adjusting the color of the entire image according to the result of white balance adjustment to achieve color correction includes: Color correction is achieved by multiplying the RGB values ​​of each pixel using the gain matrix obtained from the white balance adjustment.

[0012] Optionally, based on the pre-processed image, the step of applying an image segmentation technique to distinguish between shadow areas and non-shadow areas comprises: Increase the contrast of the image to make the difference between shadow and non-shadow areas more obvious; Converting the preprocessed image from RGB to HSV color space so that shadows appear as areas of lower brightness; Setting thresholds based on brightness or saturation to distinguish shadow areas from non-shadow areas for shadow detection; Use the opening operation to corrode the image and then dilate it to remove noise, and use the closing operation to dilate and then corrode it to fill the holes in the image; Use connected component analysis to analyze markers and determine shadow regions based on contour detection and filtering.

[0013] Optionally, the step of extracting shadow features from the detected shadow area to determine the size and position of the shadow area and predicting the impact of the shadow area on the performance of the photovoltaic cell includes: Using a connected component analysis technique or a contour detection technique, the number of pixels in the shadow region is calculated to reflect the area of ​​the shadow region, and the area of ​​the shadow region is compared with a reference size of the photovoltaic cell to obtain the proportion of the shadow region; Use contour detection technology to calculate the contour length of the shadow area and calculate the shape characteristics of the shadow area to distinguish different types of shadow areas; The extracted feature data are fused using multi-feature fusion technology, and the classification and clustering decision algorithm is used to calculate the position of the centroid or bounding box of the shadow area, and the relative position relationship between the shadow position and the preset components on the solar panel is analyzed to calculate the influence of the shadow area on the performance of the solar panel.

[0014] Optionally, the step of dividing the photovoltaic panel into a plurality of sub-arrays based on the dynamic sub-array division strategy, each sub-array independently running the multi-peak tracking algorithm, and monitoring the surface temperature of the photovoltaic cell to perform hot spot monitoring processing to accurately predict and adjust the maximum power point includes: Based on the results of shadow detection and feature extraction, clustering algorithms or rule-based algorithms are used to divide sub-arrays; Using an independent maximum power point tracking algorithm controller to track the maximum power point of each subarray, the maximum power point tracking algorithm of each subarray is adjusted according to the illumination condition and / or temperature condition of the subarray; Use microinverters or optimizers to connect the subarrays and integrate the output of all subarrays into the total output of the PV system; The output power of each sub-array is monitored, and the sub-array division and the maximum power point tracking algorithm are dynamically adjusted to adapt to the changes in the illumination conditions and / or temperature conditions.

[0015] The photovoltaic cell management method based on the Internet of Things provided in this application collects key data of photovoltaic cells and uploads the key data to the cloud; the key data is used to characterize the working state of the photovoltaic cell; the key data is analyzed, and the input working point of the photovoltaic cell is regulated by the maximum power point tracking algorithm to keep the photovoltaic cell at the maximum production efficiency to improve the key data; the input working point includes the input current value and the input voltage value; the key data is displayed through the human-computer interaction page, and early warning information is sent based on the preset path. Based on the environmental information data collected by the sensor, the algorithm can be independently judged to maintain the photovoltaic cell in a good state of production efficiency. The environmental information data collected by the sensor is uploaded to the cloud server and stored in the cloud database for persistent data storage, so that users can track historical data. When an abnormal situation occurs, the user can be notified in time through the notification channel set by the user to ensure the safety of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor.

[0017] Figure 1 This is a flow chart of a photovoltaic battery management method based on the Internet of Things according to an embodiment of the present application.

[0018] Figure 2 This is an architecture diagram of a photovoltaic battery management system based on the Internet of Things according to an embodiment of the present application.

[0019] Figure 3 Schematic diagram of the hardware architecture of a photovoltaic battery management system according to an embodiment of the present application.

[0020] Figure 4 This is a schematic diagram of the design architecture of the photovoltaic management system WeChat applet according to one embodiment of the present application.

[0021] The realization of the purpose, functional features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. The above-mentioned drawings have shown clear embodiments of this application, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the concept of this application in any way, but to illustrate the concept of this application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0022] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0023] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0024] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in this article, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this article, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination". Furthermore, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate that there are the described features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or", "and / or", "including at least one of the following" etc. used in this application can be interpreted as inclusive, or mean any one or any combination. For example, “comprising at least one of the following: A, B, C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”, and for another example, “A, B or C” or “A, B and / or C” means “any of the following: A; B; C; A and B; A and C; B and C; A and B and C”. An exception to this definition will only occur when a combination of elements, functions, steps or operations are inherently mutually exclusive in some manner.

[0025] It should be understood that, although the various steps in the flowchart in the embodiment of the present application are displayed in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and it can be performed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and their execution order is not necessarily performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0026] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0027] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0028] First embodiment This application provides a photovoltaic battery management method based on the Internet of Things. Figure 1 This is a flow chart of a photovoltaic battery management method based on the Internet of Things according to an embodiment of the present application.

[0029] like Figure 1 As shown, in one embodiment, the photovoltaic battery management method based on the Internet of Things includes: S10: Collect key data of the photovoltaic cell and upload the key data to the cloud; the key data is used to characterize the working state of the photovoltaic cell.

[0030] For example, various data of photovoltaic cells can be collected with the help of various sensors and uploaded to the cloud in real time, so that the working status of the photovoltaic cells can be obtained in time.

[0031] S20: Analyze the key data, and adjust the input operating point of the photovoltaic cell through a maximum power point tracking algorithm so that the photovoltaic cell maintains maximum production efficiency to improve the key data; the input operating point includes an input current value and an input voltage value.

[0032] For example, the maximum power point tracking algorithm can be used to track and regulate the maximum power point of the photovoltaic cell's production efficiency based on the current illuminance, temperature and humidity, and the input efficiency and performance of the battery to achieve the best performance state. The MPPT algorithm (Maximum Power Point Tracking) is a power electronics technology that aims to keep solar panels or other power generation equipment (such as wind turbines, fuel cells, etc.) at the maximum power output point through different algorithms, thereby improving their efficiency. The main purpose of the MPPT algorithm is to adjust the working state of the photovoltaic cell in real time so that it can output maximum power under the current light and temperature conditions.

[0033] S30: Displaying the key data through a human-computer interaction page, and sending warning information based on a preset path to ensure the safety of the photovoltaic cell.

[0034] For example, users can view battery-related data and perform corresponding control operations through human-computer interaction pages such as WeChat applet. At the same time, when a certain data is abnormal, the system can automatically send a reminder to the user in the form of WeChat station message, SMS or email, play an early warning role, and ensure the safety of photovoltaic batteries.

[0035] In this embodiment, the environmental information data collected by the sensor is uploaded to the cloud server and stored in the cloud database for data persistence storage, which is convenient for users to track historical data. When an abnormal situation occurs, the user can be notified in a timely manner through the notification channels set by the user, ensuring the safety of the device and improving the user experience.

[0036] Optionally, the key data includes input current and input voltage. The steps of analyzing the key data and regulating the input operating point of the photovoltaic cell through the maximum power point tracking algorithm to keep the photovoltaic cell at the maximum production efficiency to improve the key data include: Initialize the maximum power point tracking algorithm, and set the input power of the initial operating point as the input power of the previous cycle before initialization. The initial operating point includes an initial voltage value and an initial current value; Calculate the current input power of the photovoltaic cell according to the collected input current and input voltage; Compare the current input power with the input power of the previous cycle. If the current input power is higher, adjust the operating point in the same direction. If the power decreases, continue to adjust the operating point in the direction of changing the operating point.

[0037] Exemplarily, when the system starts, the maximum power point tracking algorithm needs to be initialized. This usually includes setting an initial operating point. For example, an initial voltage and current value are set. The key data of the photovoltaic cell, including input current (I_in), input voltage (V_in), and environmental parameters (such as light intensity and temperature), are continuously collected through sensors. According to the collected current and voltage data, the current output power of the photovoltaic cell can be calculated. For example, the power is calculated through the following expression: P = V_in * I_in.

[0038] The maximum power point tracking algorithm compares the current power with the power of the previous cycle. If the current power is higher, the algorithm will continue to adjust the operating point in the same direction; if the power decreases, the adjustment direction will be changed. Repeat the above process, and gradually approach the maximum power point through continuous adjustment and comparison.

[0039] Exemplarily, assume that the input voltage of a photovoltaic cell at a certain moment is V1 and the input current is I1, and the calculated power is P1. The algorithm will slightly adjust the voltage to V2, measure the new current I2, and calculate the power P2. If P2 > P1, continue to increase the voltage; if P2 < P1, decrease the voltage. Through such an iterative process, the system can find and maintain the maximum power output point of the photovoltaic cell.

[0040] When adjusting the working point, the photovoltaic cell can be operated safely to avoid overvoltage or overcurrent. The intelligent control system can effectively track the maximum power point of the photovoltaic cell, thereby improving the production efficiency of the photovoltaic cell.

[0041] Optionally, the key data includes environmental data; the maximum power point tracking algorithm includes a multi-peak tracking algorithm; The step of analyzing the key data and regulating the input working point of the photovoltaic cell by a maximum power point tracking algorithm so as to maintain the maximum power generation efficiency of the photovoltaic cell to improve the key data also includes: Using image processing technology to detect the position and size of the shadow on the photovoltaic cell, and based on the environmental data, identifying and tracking the local maximum power point based on a multi-peak tracking algorithm; Based on the dynamic sub-array division strategy, the photovoltaic panel is divided into multiple sub-arrays, each sub-array independently runs the multi-peak tracking algorithm, and monitors the surface temperature of the photovoltaic cell to perform hot spot monitoring processing to accurately predict and adjust the maximum power point.

[0042] Exemplarily, for the problem of local shadows, an algorithm that can identify and track multiple local maximum power points, such as a multi-peak tracking algorithm, is used. For shadow detection, image processing technology or other sensors can be used to detect the position and size of the shadow on the photovoltaic cell. Then a dynamic subarray division operation is performed to divide the photovoltaic cell into multiple subarrays, and each subarray independently performs a maximum power point tracking algorithm to reduce the impact of the shadow on the overall performance. In addition, hot spot monitoring can be performed at the same time, using a temperature sensor to monitor the surface temperature of the battery panel, to detect hot spots in time, and to manage the hot spot effect of the photovoltaic cell in time. Combining multi-source data such as light, temperature, current and voltage, the use of multi-sensor data fusion technology can more accurately predict and adjust the maximum power point.

[0043] Optionally, the step of using image processing technology to detect the position and size of the shadow on the photovoltaic cell includes: Based on a preset resolution and frame rate, an original surface image of the photovoltaic cell is collected, and the collected original surface image is adaptively preprocessed to improve image quality, thereby obtaining a preprocessed image; Based on the preprocessed image, applying image segmentation technology to distinguish shadow areas from non-shadow areas, and using a machine learning algorithm to classify shadow and non-shadow areas; Shadow features are extracted from the detected shadow area to determine the size and position of the shadow area and predict the impact of the shadow area on the performance of the photovoltaic cell.

[0044] Image processing techniques can effectively detect the position and size of shadows on photovoltaic cells. For example, ensure that the image acquisition device has good resolution and sufficient frame rate to clearly capture shadow details. Images of the panels can be taken using a camera or drone installed near the photovoltaic cells. Optionally, the captured images can be pre-processed, including denoising, contrast enhancement, color correction, etc., to improve image quality.

[0045] For example, the application of image segmentation techniques (such as threshold segmentation, edge detection, region growing, etc.) can distinguish between shadow areas and non-shadow areas. Machine learning algorithms (such as support vector machines, neural networks) can also be used to classify shadow and non-shadow areas. Extracting features such as area, perimeter, shape, position, etc. from the detected shadow area can accurately predict the impact of the shadow area on the performance of the photovoltaic cell, which can be used for further analysis and decision-making. Optionally, the step of adaptively preprocessing the acquired original surface image to improve image quality comprises: Based on the original surface image, a white balance adjustment is performed using a statistical method, and the image contrast is dynamically adjusted according to a histogram of the image to obtain an adjusted image; Using an algorithm based on Retinex theory to perform illumination correction and noise reduction on the adjusted image to obtain a noise-reduced image; An adaptive threshold is selected for the denoised image based on a local area method to perform image segmentation based on the threshold, and image enhancement is performed based on different illumination conditions to obtain a preprocessed image.

[0046] For example, taking into account the changes in lighting conditions, an adaptive preprocessing step is an important step to ensure that the image processing system can work effectively under different lighting conditions. Changes in lighting conditions can cause color deviations in images. Automatic white balance adjustment can eliminate this deviation and keep the image consistent in color under different lighting conditions. Statistical methods (such as the gray world hypothesis, perfect reflection method, etc.) can be used to automatically adjust the white balance.

[0047] Contrast enhancement can improve the visual effect of the image, but it needs to be adjusted dynamically under different lighting conditions. Light correction technology can adjust the brightness of the image to keep it consistent under different lighting conditions. For example, algorithms based on Retinex theory (such as SSR, MSR, etc.) can be used for light correction, and histogram equalization or adaptive histogram equalization technology can be used to automatically adjust the contrast according to the histogram of the image. In addition, denoising can reduce the impact of noise on image quality. Denoising can be performed using algorithms such as bilateral filtering and non-local mean filtering, which can maintain the edge information of the image while denoising.

[0048] Optionally, the threshold can be adaptively selected using the Otsu method, an iterative method, or a method based on a local area, and adaptive image enhancement techniques such as adaptive histogram stretching, adaptive sharpening, etc. can also be used.

[0049] For example, according to the quality of the preprocessed image, the preprocessing parameters can be adjusted in real time. Machine learning algorithms, such as reinforcement learning, can be used to optimize the selection of preprocessing parameters. Thus, high-quality images can be obtained under different lighting conditions, providing a reliable data basis for subsequent shadow detection and photovoltaic cell performance analysis.

[0050] Optionally, the step of adaptively preprocessing the acquired original surface image to improve image quality further includes: The preprocessed image is converted from the RGB color space to the CIE Lab color space, the neutral color area in the image is found, the average values ​​of the R, G, and B components of the entire image are calculated, and normalization is performed to obtain a color correction gain to correct the color cast in the preprocessed image.

[0051] According to the result of white balance adjustment, the color of the whole image is adjusted to achieve color correction; The rectified image is converted back from Lab to RGB color space to optimize the pre-processed image.

[0052] Color correction is an important step in the preprocessing of the acquired images, especially when the lighting conditions change, to eliminate the effects of uneven lighting or color cast on image quality. Exemplarily, a conversion can be made from RGB to CIE Lab color space. The L component in the Lab color space represents brightness, and the a and b components represent color information, which makes color correction more intuitive and independent of brightness. The grayscale world hypothesis or perfect reflection method can be used to correct the color cast in the image so that white or gray objects appear the same color under different lighting conditions. It is assumed that the average value in the image should be close to a neutral color (white or gray). The color correction gain is obtained by calculating the average value of the R, G, and B components of the entire image and then normalizing these values. Areas in the image that are considered to be perfect reflections (i.e., neutral colors) can be found, and then the color correction gain is calculated based on these areas.

[0053] Optionally, the step of adjusting the color of the entire image according to the result of white balance adjustment to achieve color correction includes: Color correction is achieved by multiplying the RGB values ​​of each pixel using the gain matrix obtained from the white balance adjustment.

[0054] For example, the gain matrix obtained from the white balance adjustment can be used to multiply the RGB value of each pixel to achieve color correction. The corrected image is converted from Lab back to RGB color space for display and further processing. This effectively corrects the color deviation caused by changes in lighting conditions, thereby improving the accuracy and robustness of subsequent image processing steps (such as image segmentation, feature extraction, etc.).

[0055] The sample code is as follows: (Python, using OpenCV library) import cv2 import numpy as np # Read the image image = cv2.imread('solar_panel.jpg') # Convert to Lab color space lab_image = cv2.cvtColor(image, cv2.COLOR_BGR2LAB) # Separate L, a, b channels L, a, b = cv2.split(lab_image) # Apply grayscale world assumption for white balance # Calculate the average of channels a and b a_mean = np.mean(a) b_mean = np.mean(b) # Calculate gain a_gain = 128 / a_mean b_gain = 128 / b_mean # Apply gain a_corrected = np.clip(a * a_gain, 0, 255).astype(np.uint8) b_corrected = np.clip(b * b_gain, 0, 255).astype(np.uint8) # Merge L, a, b channels lab_corrected = cv2.merge([L, a_corrected, b_corrected]) # Convert back to BGR color space image_corrected = cv2.cvtColor(lab_corrected, cv2.COLOR_LAB2BGR) # Display the corrected image cv2.imshow('Color Corrected Image', image_corrected) cv2.waitKey(0) cv2.destroyAllWindows() Optionally, based on the pre-processed image, the step of applying an image segmentation technique to distinguish between shadow areas and non-shadow areas comprises: Increase the contrast of the image to make the difference between shadow and non-shadow areas more obvious; Converting the preprocessed image from RGB to HSV color space so that shadows appear as areas of lower brightness; Setting thresholds based on brightness or saturation to distinguish shadow areas from non-shadow areas for shadow detection; Use the opening operation to corrode the image and then dilate it to remove noise, and use the closing operation to dilate and then corrode it to fill the holes in the image; Use connected component analysis to analyze markers and determine shadow regions based on contour detection and filtering.

[0056] For example, image segmentation techniques may be applied to distinguish shadow areas from non-shadow areas for photovoltaic cell shadow detection. Histogram equalization, adaptive histogram equalization or local contrast enhancement techniques may be used to increase the contrast of the image and make the difference between shadow areas and non-shadow areas more obvious.

[0057] Convert from RGB to HSV (hue, saturation, brightness) color space. In HSV space, shadows usually appear as areas with lower brightness (V channel), thus choosing a color space that is more suitable for shadow detection.

[0058] Exemplarily, a threshold can be set based on brightness or saturation, and areas below the threshold are considered shadows. Region growing or region splitting and merging methods can be used, or edge detection algorithms such as Canny edge detection can be used, followed by edge connection. Use appropriate thresholds or methods to distinguish shadow areas and non-shadow areas. Then use an open operation (erosion followed by expansion) to remove noise, and a closed operation (expansion followed by corrosion) to fill holes to remove noise and small areas and smooth edges. Finally, use connected component analysis to mark and select shadow areas of interest, or use contour detection and screening to further optimize the segmentation results to effectively segment shadow areas and non-shadow areas on the photovoltaic cell.

[0059] Optionally, the step of using an opening operation to corrode the image and then dilate it to remove noise, and using a closing operation to dilate and then corrode it to fill the holes in the image includes: One or more thresholds are set based on the brightness or color information of the image, the image is converted into a binary image, and the shadow area is separated by a dynamic threshold; and / or, The image is divided into multiple regions, and the shadow area is determined based on the pixel characteristics in the region; and / or, Edge detection operators are used to detect edges that mark non-shadow regions, and then shadow regions are separated through edge connection operations for edge-based segmentation.

[0060] Exemplarily, in the shadow detection process, one or more thresholds can be set based on the brightness or color information of the image to convert the image into a binary image, in which the shadow area is usually displayed as a darker area. , morphological operations and post-processing. For example, in HSV or YCrCb color space, shadows usually have lower brightness values. By selecting an appropriate threshold, the shadow area can be separated. Exemplarily, the image can be divided into multiple regions using techniques such as region growing and region splitting and merging, and then the shadow area is determined based on the pixel characteristics (such as color, texture, etc.) in the region. Exemplarily, the edge of the shadow area is usually fuzzy, and there is an obvious edge between the shadow area and the non-shadow area. Edge detection operators such as Canny and Sobel can be used to detect the edge, and then the shadow area is separated by edge connection and other operations. Exemplarily, morphological operations are a series of operations based on the shape of the image, which are used to process details in the image, such as removing noise, connecting broken areas, etc.

[0061] Exemplarily, the erosion process is a process of reducing the bright area (or dark area) in the image and eliminating small bright spots (or small dark spots) in the image to remove noise and separate closely connected objects. Exemplarily, the dilation process is a process of filling small holes in the image by expanding the bright area (or dark area) in the image to connect adjacent objects. In the opening operation, erosion is performed first and then dilation is performed, which is used to remove noise and small objects, and can smooth the contours of larger objects and remove small noise points. In the closing operation, dilation is performed first and then erosion is performed, which is used to fill holes and connect adjacent objects, and can fill small holes in objects and connect adjacent objects.

[0062] Exemplarily, post-processing is performed after shadow detection and morphological operations, which can further optimize the segmentation results and make them more suitable for subsequent analysis and processing. In the process of connected component analysis, each connected area (white area) in the binary image can be marked as a component, and the shadow area of ​​interest can be selected, or the noise area of ​​no interest can be removed. At the same time, the contours in the binary image are detected, and then screened according to the attributes of the contours (such as area, perimeter, etc.) to select or exclude specific shadow areas, or further shadow geometry analysis can be performed to more effectively detect and segment the shadow areas on the photovoltaic cells.

[0063] Optionally, the step of extracting shadow features from the detected shadow area to determine the size and position of the shadow area and predicting the impact of the shadow area on the performance of the photovoltaic cell includes: Using a connected component analysis technique or a contour detection technique, the number of pixels in the shadow region is calculated to reflect the area of ​​the shadow region, and the area of ​​the shadow region is compared with a reference size of the photovoltaic cell to obtain the proportion of the shadow region; Use contour detection technology to calculate the contour length of the shadow area and calculate the shape characteristics of the shadow area to distinguish different types of shadow areas; The extracted feature data are fused using multi-feature fusion technology, and the classification and clustering decision algorithm is used to calculate the position of the centroid or bounding box of the shadow area, and the relative position relationship between the shadow position and the preset components on the solar panel is analyzed to calculate the influence of the shadow area on the performance of the solar panel.

[0064] For example, the area can reflect the size of the shadow area, and the perimeter can reflect the shape complexity of the shadow area. The number of pixels in the shadow area can be calculated using a connected component analysis or contour detection method; and the contour length of the shadow area can be calculated using a contour detection technique. For example, by calculating the shape features of the shadow area, such as circularity, rectangularity, slenderness, etc., different types of shadows can be distinguished, and the location of the centroid or bounding box of the shadow area can be calculated to determine the specific location of the shadow area.

[0065] During the feature analysis process, the size of the shadow area can be determined based on the extracted area features; and the specific position of the shadow area on the photovoltaic cell can be determined based on the extracted position features.

[0066] The relative position relationship between the shadow position and other components on the panel (such as battery cells, bus bars, etc.) can be analyzed to evaluate the impact of the shadow on the performance of the panel; the size of the shadow area can be compared with the reference size of the photovoltaic cell to evaluate the impact of the shadow on the performance of the panel.

[0067] For example, data fusion techniques, such as multi-feature fusion, multi-scale analysis, etc., can be used to fuse the extracted feature data to obtain more comprehensive information. Decision algorithms, such as classification, clustering, etc., can be used to classify or cluster the shadow area to determine the size and position of the shadow area based on the analysis results.

[0068] Optionally, the step of dividing the photovoltaic panel into a plurality of sub-arrays based on the dynamic sub-array division strategy, each sub-array independently running the multi-peak tracking algorithm, and monitoring the surface temperature of the photovoltaic cell to perform hot spot monitoring processing to accurately predict and adjust the maximum power point includes: Based on the results of shadow detection and feature extraction, clustering algorithms or rule-based algorithms are used to divide sub-arrays; Using an independent maximum power point tracking algorithm controller to track the maximum power point of each subarray, the maximum power point tracking algorithm of each subarray is adjusted according to the illumination condition and / or temperature condition of the subarray; Use microinverters or optimizers to connect the subarrays and integrate the output of all subarrays into the total output of the PV system; The output power of each sub-array is monitored, and the sub-array division and the maximum power point tracking algorithm are dynamically adjusted to adapt to the changes in the illumination conditions and / or temperature conditions.

[0069] After the location and size of the shadow are identified in the photovoltaic cell, a dynamic subarray division strategy can be adopted to optimize the performance of the photovoltaic system. The purpose of dynamic subarray division is to divide the panels affected by the shadow into independent subarrays so that each subarray can independently perform maximum power point tracking (maximum power point tracking algorithm). Exemplarily, based on the results of shadow detection and feature extraction, the location and size of the shadow area and their potential impact on the output power of the panel are determined. According to the location and size of the shadow, a clustering algorithm or a rule-based method can be used to divide the subarray. For example, adjacent battery cells affected by the shadow can be divided into a subarray. Optionally, an independent maximum power point tracking algorithm controller can be used to perform maximum power point tracking on each subarray to optimize its output power, and the maximum power point tracking algorithm of each subarray can be adjusted according to the specific lighting conditions and temperature conditions of the subarray.

[0070] For example, microinverters or optimizers can be used to connect the subarrays, and the outputs of all subarrays can be integrated into the total output of the photovoltaic system to achieve efficient energy management and maximize the overall system performance. The performance of each subarray, including output power, efficiency, etc., can be monitored to dynamically adjust the subarray division and maximum power point tracking algorithm strategy to adapt the photovoltaic cell system to changes in light and temperature.

[0071] Through dynamic sub-array division and independent maximum power point tracking algorithm, the performance of photovoltaic systems under partial shadow conditions can be significantly improved, thereby improving the overall photovoltaic power generation efficiency and reliability.

[0072] Second embodiment The present application provides a photovoltaic battery management system based on the Internet of Things, and applies the photovoltaic battery management method based on the Internet of Things. Figure 2 This is an architecture diagram of a photovoltaic battery management system based on the Internet of Things according to an embodiment of the present application.

[0073] like Figure 2 As shown, in one embodiment, the main architecture of the photovoltaic battery management system based on the Internet of Things includes three modules, namely, a collection module, a control module and a networking module.

[0074] Among them, the acquisition module mainly collects data in three aspects to provide data reference for the control module, including: energy supply data collection, energy output data collection and environmental data collection. Energy supply data collection mainly involves the electrical energy parameters converted by photovoltaic cells through light, including input current, input voltage and input power. Energy output data collection mainly collects the maximum power point after the photovoltaic cell is input into the control board, and tracks the output current, voltage and power through the control system MPPT algorithm.

[0075] The control module is based on a single-chip microcomputer board. By analyzing the effective data collected by the acquisition module, the programmed MPPT algorithm is used to intelligently adjust the output duty cycle to achieve the effect of improving energy efficiency. While controlling, data will be transmitted to the networking module through the communication interface.

[0076] The networking module is divided into three implementation points, namely data transmission, front-end page display and user interaction. Among them, data transmission is through the WIFI module on the microcontroller, and the data is uploaded to the cloud platform according to the corresponding protocol. The front-end page data display adopts the form of mini-programs, and the front-end page is built in the mini-program to display the collected relevant data. User interaction is also implemented on the mini-program side, and the corresponding control instructions are sent to the corresponding cloud platform through POST requests.

[0077] Figure 3 Schematic diagram of the hardware architecture of a photovoltaic battery management system according to an embodiment of the present application.

[0078] like Figure 3 As shown, in one embodiment, the photovoltaic cell control system is a system built with the STM32F103RCT6 development board as the core.

[0079] The MCU module is responsible for analyzing and processing the data transmitted by the sensor, and uploading the data to the cloud platform through the ESP01S module. The STM32 analyzes the collected data and intelligently controls the algorithm board, while receiving control instructions issued by the cloud platform to complete the corresponding control operations.

[0080] The solar array simulation is used to simulate a solar panel. It can simulate a solar cell connected to the system and generating electricity. The external 3.3V power supply is used to power the connected peripherals. The power supply capacity of the development board itself is weak and cannot support the use of multiple peripherals. The peripherals can be connected to the 3.3V power supply on the power board to achieve self-sufficiency.

[0081] The solar array simulates a solar panel, which is used to simulate a solar cell connected to the system and generating electricity. The external 3.3V power supply is used to power the connected peripherals. The power supply of the development board itself is weak and cannot support multiple peripherals. The peripherals can be connected to the 3.3V power supply on the power board to achieve self-sufficiency.

[0082] Figure 4 This is a schematic diagram of the design architecture of the photovoltaic management system WeChat applet according to one embodiment of the present application.

[0083] like Figure 4 As shown, in one embodiment, the photovoltaic cell control system WeChat applet adopts the native layered architecture design of the WeChat applet, which is divided into the View layer and the App Service layer (i.e., the logic layer). Through this layered structure, the code is clearly divided into the view layer and the logic layer. In the front-end UI design interface, the corresponding display controls and operation controls are carefully designed.

[0084] In the back-end data logic processing part, data binding and user interaction logic processing are performed. After the code is layered, developers can handle the required parts more effectively and focus on the development level they need. In the subsequent maintenance and upgrade process, code modifications will not affect irrelevant code, thereby reasonably reducing the coupling degree of the system.

[0085] App Service layer: Mainly written in JavaScript, it is mainly responsible for processing business data, performing logic processing, initiating data requests, and calling interfaces in the program. All logical interaction functions are implemented by JavaScript. The role of the logic layer is to process business data, pass it to the view layer for rendering, and receive feedback from events generated by the view layer. In WeChat mini-programs, developers can register using the App (OBJECT) method to specify the life cycle function of the mini-program. At the same time, the logic layer is also responsible for registering pages, processing page logic, and managing page data.

[0086] View layer: It is composed of Wxml and Wxss, and is responsible for displaying the front-end interface. Wxml corresponds to HTML in Web applications, which is used to describe the page structure; Wxss corresponds to CSS in Web applications, which is used to describe the page style. The view layer receives data from the logic layer and renders it into a user-visible interface.

[0087] The photovoltaic battery management system of this embodiment uses various sensors to collect various data of photovoltaic cells and uploads them to the cloud in real time. Based on the environmental information data collected by the sensor, the algorithm is independently researched and judged to maintain the photovoltaic cell in a good state of production efficiency. According to the current illuminance, temperature and humidity, and the input efficiency and performance of the battery, the MPPT algorithm is used to track and control the maximum power point of the photovoltaic cell to achieve the best performance state. The environmental information data collected by the sensor can be uploaded to the cloud server and stored in the cloud database for persistent data storage, which is convenient for users to track historical data. At the same time, when a certain data is abnormal, the system can automatically send a reminder to the user in the form of a WeChat station letter or email, play an early warning role, and ensure the safety of the photovoltaic cell. When an abnormal situation occurs, the user can be notified in time through the notification channel set by the user to ensure the safety of the equipment. In addition, the user can view the battery-related data and perform corresponding control operations through the WeChat applet. Users can conveniently send corresponding operation instructions to the current online device on the WeChat terminal to achieve remote control.

[0088] The photovoltaic cell management method based on the Internet of Things provided in this application collects key data of photovoltaic cells and uploads the key data to the cloud; the key data is used to characterize the working state of the photovoltaic cell; the key data is analyzed, and the input working point of the photovoltaic cell is regulated by the maximum power point tracking algorithm to keep the photovoltaic cell at the maximum production efficiency to improve the key data; the input working point includes the input current value and the input voltage value; the key data is displayed through the human-computer interaction page, and early warning information is sent based on the preset path. Based on the environmental information data collected by the sensor, the algorithm can be independently judged to maintain the photovoltaic cell in a good state of production efficiency. The environmental information data collected by the sensor is uploaded to the cloud server and stored in the cloud database for persistent data storage, so that users can track historical data. When an abnormal situation occurs, the user can be notified in time through the notification channel set by the user to ensure the safety of the equipment and improve the user experience.

[0089] It should be noted that in the present application, step codes such as S10, S20, etc. are used for the purpose of expressing the corresponding content more clearly and concisely, and do not constitute a substantial limitation on the sequence. When implementing the step, those skilled in the art may execute S20 first and then S10, etc., but these should all be within the scope of protection of the present application.

[0090] In the embodiments of the device and storage medium provided in the present application, all technical features of any of the above-mentioned method embodiments may be included, and the expanded and explained contents of the specification are basically the same as those of the above-mentioned method embodiments, and will not be repeated here.

[0091] The embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer executes the methods in the above various possible implementation modes.

[0092] An embodiment of the present application also provides a chip, including a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that a device equipped with the chip executes the methods in various possible implementation modes as described above.

[0093] It is understood that the above scenarios are only examples and do not constitute a limitation on the application scenarios of the technical solutions provided in the embodiments of the present application. The technical solutions of the present application can also be applied to other scenarios. For example, it is known to those skilled in the art that with the evolution of device architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0094] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0095] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0096] The units in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0097] In the present application, the same or similar terminology concepts, technical solutions and / or application scenario descriptions are generally described in detail only the first time they appear. When they appear again later, they are generally not repeated for the sake of brevity. When understanding the technical solutions and other contents of the present application, for the same or similar terminology concepts, technical solutions and / or application scenario descriptions that are not described in detail later, reference can be made to the previous related detailed descriptions.

[0098] In the present application, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] The various technical features of the technical solution of the present application can be arbitrarily combined. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of the present application.

[0100] The above are only preferred embodiments of the present application, and the application scope of the present application is not limited thereto. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the application protection scope of the present application.

Claims

1. A photovoltaic battery management method based on the Internet of Things, characterized in that: include: Collect key data of photovoltaic cells and upload the key data to the cloud; The key data is used to characterize the working state of the photovoltaic cell; Analyze the key data, and adjust the input working point of the photovoltaic cell through a maximum power point tracking algorithm so that the photovoltaic cell maintains maximum power generation efficiency to improve the key data; the input working point includes an input current value and an input voltage value; The key data is displayed through a human-computer interaction page, and early warning information is sent based on a preset path to ensure the safety of the photovoltaic cell.

2. The photovoltaic battery management method based on the Internet of Things according to claim 1, characterized in that: The key data includes input current and input voltage; the step of analyzing the key data and regulating the input working point of the photovoltaic cell by a maximum power point tracking algorithm so that the photovoltaic cell maintains maximum power generation efficiency to improve the key data includes: Initializing the maximum power point tracking algorithm, setting the input power of an initial working point as the input power of a cycle before initialization, the initial working point including an initial voltage value and an initial current value; Calculating the current input power of the photovoltaic cell according to the collected input current and input voltage; The current input power is compared with the input power of the previous cycle. If the current input power is higher, the operating point is adjusted in the same direction. If the power is lower, the operating point is continuously adjusted in the direction of changing the operating point.

3. A photovoltaic battery management method based on the Internet of Things according to claim 2, characterized in that: The key data includes environmental data; the maximum power point tracking algorithm includes a multi-peak tracking algorithm; The step of analyzing the key data and regulating the input working point of the photovoltaic cell by a maximum power point tracking algorithm so as to maintain the maximum power generation efficiency of the photovoltaic cell to improve the key data also includes: Using image processing technology to detect the position and size of the shadow on the photovoltaic cell, and based on the environmental data, identifying and tracking the local maximum power point based on a multi-peak tracking algorithm; Based on the dynamic sub-array division strategy, the photovoltaic panel is divided into multiple sub-arrays, each sub-array independently runs the multi-peak tracking algorithm, and monitors the surface temperature of the photovoltaic cell to perform hot spot monitoring processing to accurately predict and adjust the maximum power point.

4. A photovoltaic battery management method based on the Internet of Things according to claim 3, characterized in that: The steps for detecting the location and size of the shadow on the photovoltaic cell using image processing technology include: Based on a preset resolution and frame rate, an original surface image of the photovoltaic cell is collected, and the collected original surface image is adaptively preprocessed to improve image quality, thereby obtaining a preprocessed image; Based on the preprocessed image, applying image segmentation technology to distinguish shadow areas from non-shadow areas, and using a machine learning algorithm to classify shadow and non-shadow areas; Shadow features are extracted from the detected shadow area to determine the size and position of the shadow area and predict the impact of the shadow area on the performance of the photovoltaic cell.

5. A photovoltaic battery management method based on the Internet of Things according to claim 4, characterized in that: The step of adaptively preprocessing the collected original surface image to improve the image quality comprises: Based on the original surface image, a white balance adjustment is performed using a statistical method, and the image contrast is dynamically adjusted according to a histogram of the image to obtain an adjusted image; Using an algorithm based on Retinex theory to perform illumination correction and noise reduction on the adjusted image to obtain a noise-reduced image; An adaptive threshold is selected for the denoised image based on a local area method to perform image segmentation based on the threshold, and image enhancement is performed based on different illumination conditions to obtain a preprocessed image.

6. A photovoltaic battery management method based on the Internet of Things according to claim 5, characterized in that: The step of adaptively preprocessing the collected original surface image to improve the image quality also includes: The preprocessed image is converted from the RGB color space to the CIE Lab color space, the neutral color area in the image is found, the average values ​​of the R, G, and B components of the entire image are calculated, and normalization is performed to obtain a color correction gain to correct the color cast in the preprocessed image. According to the result of white balance adjustment, the color of the whole image is adjusted to achieve color correction; The rectified image is converted back from Lab to RGB color space to optimize the pre-processed image.

7. A photovoltaic battery management method based on the Internet of Things according to claim 6, characterized in that: The step of adjusting the color of the entire image according to the result of the white balance adjustment to achieve color correction includes: Color correction is achieved by multiplying the RGB values ​​of each pixel using the gain matrix obtained from the white balance adjustment.

8. The photovoltaic battery management method based on the Internet of Things according to claim 7, characterized in that: Based on the pre-processed image, the step of applying image segmentation technology to distinguish shadow areas and non-shadow areas includes: Increase the contrast of the image to make the difference between shadow and non-shadow areas more obvious; Converting the preprocessed image from RGB to HSV color space so that shadows appear as areas of lower brightness; Setting thresholds based on brightness or saturation to distinguish shadow areas from non-shadow areas for shadow detection; Use the opening operation to corrode the image and then dilate it to remove noise, and use the closing operation to dilate and then corrode it to fill the holes in the image; Use connected component analysis to analyze markers and determine shadow regions based on contour detection and filtering.

9. The photovoltaic battery management method based on the Internet of Things according to claim 8, characterized in that: The step of extracting shadow features from the detected shadow area to determine the size and position of the shadow area and predicting the influence of the shadow area on the performance of the photovoltaic cell comprises: Using a connected component analysis technique or a contour detection technique, the number of pixels in the shadow region is calculated to reflect the area of ​​the shadow region, and the area of ​​the shadow region is compared with a reference size of the photovoltaic cell to obtain the proportion of the shadow region; Use contour detection technology to calculate the contour length of the shadow area and calculate the shape characteristics of the shadow area to distinguish different types of shadow areas; The extracted feature data are fused using multi-feature fusion technology, and the classification and clustering decision algorithm is used to calculate the position of the centroid or bounding box of the shadow area, and the relative position relationship between the shadow position and the preset components on the solar panel is analyzed to calculate the influence of the shadow area on the performance of the solar panel.

10. A photovoltaic battery management method based on the Internet of Things according to claim 9, characterized in that: The steps of dividing the photovoltaic panel into a plurality of sub-arrays based on the dynamic sub-array division strategy, each sub-array independently running the multi-peak tracking algorithm, and monitoring the surface temperature of the photovoltaic cell to perform hot spot monitoring processing to accurately predict and adjust the maximum power point include: Based on the results of shadow detection and feature extraction, clustering algorithms or rule-based algorithms are used to divide sub-arrays; Using an independent maximum power point tracking algorithm controller to track the maximum power point of each subarray, the maximum power point tracking algorithm of each subarray is adjusted according to the illumination condition and / or temperature condition of the subarray; Use microinverters or optimizers to connect the subarrays and integrate the output of all subarrays into the total output of the PV system; The output power of each sub-array is monitored, and the sub-array division and the maximum power point tracking algorithm are dynamically adjusted to adapt to the changes in the illumination conditions and / or temperature conditions.

Images