Method and apparatus for automatically mapping inverter of photovoltaic module

Abstract

A method for automatically mapping an inverter of a photovoltaic module according to one aspect may comprise the steps of: receiving an identification information list of a module level power electronics (MLPE) device corresponding to each of a plurality of installed photovoltaic modules; receiving a first image captured by using a drone and including a plurality of first codes and a state in which the photovoltaic modules are installed; calculating installation information related to the plurality of photovoltaic modules from the first image and generating a first layout on the basis of the installation information; identifying the plurality of first codes included in the first image so as to acquire location information and identification information of the plurality of MLPE devices corresponding to the plurality of first codes; and generating a second layout in which the first layout is modified by reflecting the acquired location information and identification information of the plurality of MLPE devices.

Description

Method and device for automatically mapping inverters of solar modules

[0001] The present invention relates to a method and device for automatically mapping an inverter of a solar module, and more particularly, to a method and device for automatically mapping an inverter of a solar module using a drone.

[0002] With the recent rise in interest in eco-friendly energy technologies, the installation of solar power generation systems, which utilize sunlight to generate energy, is on the rise. Solar power systems generate electricity by collecting solar energy through photovoltaic modules. This electricity is then fed into the household power grid for household use or stored in batteries for later use. Power generation through solar power systems is environmentally friendly and can reduce electricity bills in the long term, making it a popular choice.

[0003] Typically, a solar power generation system consists of multiple photovoltaic (PV) modules, each of which includes a microinverter that converts the generated energy. After installing multiple PV modules, installers must map them onto a layout. This process requires manually scanning the codes containing the identification information for each PV module or microinverter, then manually correlating the identification information with the location of each PV module or microinverter. Therefore, various methods are being studied to simplify this process.

[0004] The background technology described above is technical information that the inventor possessed for the purpose of deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be considered as publicly known technology disclosed to the general public prior to the application for the present invention.

[0005] One object of the present invention is to provide a method for simultaneously recognizing identification information of a plurality of solar modules or micro-inverters and easily managing the same.

[0006] One object of the present invention is to utilize a drone to provide a layout diagram of a plurality of solar modules capable of easily collecting and managing location information of solar modules including micro inverters.

[0007] One object of the present invention is to generate more accurate mapping results by actually reflecting the on-site conditions by modifying a layout by calculating installation information including tilt angle and azimuth angle from an image including a state in which a plurality of solar modules are installed.

[0008] One object of the present invention is to optimize a layout while maintaining visual consistency by generating a modified layout that rotates the layout and excludes text containing identification information corresponding to installation information.

[0009] The problems addressed by the present invention are not limited to those mentioned above. Other problems and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through examples of the present invention. Furthermore, it will be appreciated that the problems and advantages addressed by the present invention can be realized by the means and combinations thereof set forth in the claims.

[0010] In order to solve the above-described problem of the present invention, a method for automatically mapping an inverter of a solar module according to an embodiment of the present invention comprises the steps of: receiving a list of identification information of MLPE (Module Level Power Electronics) devices each corresponding to a plurality of installed solar modules; receiving a first image including a plurality of first codes and an installed state of the solar modules photographed using a drone; calculating installation information related to the plurality of solar modules from the first image and generating a first layout drawing based on the installation information; recognizing the plurality of first codes included in the first image to obtain location information and identification information of the plurality of MLPE devices corresponding to the plurality of first codes; And a step of generating a second layout plan by modifying the first layout plan by reflecting the location information and identification information of the plurality of MLPE devices obtained above; and the obtaining step may include a step of, when recognition of one or more of the plurality of first codes included in the first image is impossible, moving the drone to obtain one or more second images corresponding to the one or more first codes that are impossible to recognize, and obtaining location information and identification information of the plurality of MLPE devices based on the obtained second images.

[0011] In the present invention, the obtaining step may include a step of moving the drone so as to be closer to one of the plurality of MLPE devices by a preset distance or less, capturing and receiving a plurality of second images including at least one of the plurality of first codes, and recognizing the plurality of first codes included in the plurality of second images to obtain location information and identification information of the plurality of MLPE devices corresponding to the first codes.

[0012] In the present invention, the obtaining step may include a step of recognizing the first code included in the first image, identifying coordinate information of the first code, and obtaining location information of the micro inverter using the coordinate information.

[0013] In the present invention, the step of generating the first layout may include the step of receiving a tilt angle and an azimuth measured corresponding to the first image by an acceleration sensor and a gyroscope sensor provided in the drone; and the step of determining the tilt angle and the azimuth as installation information related to the plurality of solar modules.

[0014] In the present invention, the step of generating the first layout may include the steps of extracting a roof and a ground on which the plurality of solar modules are installed from the first image and calculating a tilt angle as an inclination of the roof with respect to the ground; calculating an azimuth of the plurality of solar modules based on information included in metadata of the first image and the tilt angle; and determining the tilt angle and the azimuth angle as installation information related to the plurality of solar modules.

[0015] In the present invention, the step of generating the first layout includes the step of generating installation information related to the plurality of solar modules corresponding to the first image using a deep neural network model that is pre-trained to generate installation information related to the plurality of solar modules corresponding to the first image including the state in which the plurality of solar modules are installed; and the deep neural network model may be a model trained in a supervised learning manner by using the first image including the state in which the plurality of solar modules are installed as input and training data having the tilt angle and azimuth angle of the solar modules as labels.

[0016] A device for automatically mapping an inverter of a solar module according to another aspect, comprising: at least one processor; And at least one memory, wherein the at least one processor is configured to receive a list of identification information of MLPE (Module Level Power Electronics) devices each corresponding to a plurality of installed solar modules, receive a first image including a plurality of first codes and an installed state of the solar modules photographed using a drone, calculate installation information related to the plurality of solar modules from the first image, generate a first layout diagram based on the installation information, recognize the plurality of first codes included in the first image to obtain location information and identification information of the plurality of MLPE devices corresponding to the plurality of first codes, and generate a second layout diagram that modifies the first layout diagram by reflecting the obtained location information and identification information of the plurality of MLPE devices, and the at least one processor may be configured to, when recognition of any one or more of the plurality of first codes included in the first image is impossible, move the drone to obtain one or more second images corresponding to the one or more first codes that are impossible to recognize, and obtain location information and identification information of the plurality of MLPE devices based on the obtained second images.

[0017] In addition, other methods for implementing the present invention, other systems, and computer-readable recording media storing a computer program for executing the method may be further provided.

[0018] Other aspects, features and advantages other than those described above will become apparent from the following drawings, claims and detailed description of the invention.

[0019] According to the present invention, it is possible to easily manage a plurality of pieces of identification information by simultaneously recognizing the identification information of a plurality of micro inverters.

[0020] In addition, by generating a layout based on the location information of solar modules corresponding to multiple micro-inverters, location information of solar modules including micro-inverters can be easily collected and managed.

[0021] In addition, by calculating the tilt angle and azimuth from images containing the installed status of multiple solar modules taken using a drone and adding them to the layout, more accurate mapping results can be obtained by actually reflecting the on-site conditions.

[0022] In addition, by outputting a layout diagram containing identification information and location information of multiple solar modules or micro inverters and installation information including tilt angle and azimuth information to the user's terminal, the user can easily check and correct the location information.

[0023] In addition, a modified layout plan that rotates the layout plan and excludes text containing identification information corresponding to the installation information can be generated and output to the user's terminal, thereby optimizing the layout plan while maintaining visual consistency.

[0024] In addition, if the identification information of the micro inverter is lost or cannot be recognized, it can be replaced by recognizing the identification information of the solar module, thereby improving convenience of use.

[0025] The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0026] FIG. 1 is a block diagram schematically illustrating the configuration of a device for automatically mapping an inverter of a solar module according to one embodiment.

[0027] FIG. 2 is a flowchart illustrating a method for automatically mapping an inverter of a solar module according to one embodiment.

[0028] FIGS. 3A and 3B are examples of first images captured using a drone according to one embodiment.

[0029] FIGS. 4A and 4B are examples of second images taken using a drone according to one embodiment.

[0030] FIGS. 5A and 5B are exemplary diagrams illustrating the production of installation information from a first image according to one embodiment.

[0031] FIG. 6 is an exemplary diagram illustrating a process of outputting a second layout drawing based on installation information according to one embodiment.

[0032] A method for automatically mapping an inverter of a solar module according to one aspect comprises the steps of: receiving a list of identification information of MLPE (Module Level Power Electronics) devices each corresponding to a plurality of installed solar modules; receiving a first image including a plurality of first codes and an installed state of the solar modules, the first image being photographed using a drone; calculating installation information related to the plurality of solar modules from the first image, and generating a first layout based on the installation information; recognizing the plurality of first codes included in the first image to obtain location information and identification information of the plurality of MLPE devices corresponding to the plurality of first codes; And a step of generating a second layout plan by modifying the first layout plan by reflecting the location information and identification information of the plurality of MLPE devices obtained above; and the obtaining step may include a step of, when recognition of one or more of the plurality of first codes included in the first image is impossible, moving the drone to obtain one or more second images corresponding to the one or more first codes that are impossible to recognize, and obtaining location information and identification information of the plurality of MLPE devices based on the obtained second images.

[0033] The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments presented below, but may be implemented in various different forms, and it should be understood that it includes all transformations, equivalents, and substitutes included in the spirit and technical scope of the present invention. The embodiments presented below are provided to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention. In describing the present invention, if a detailed description of a related known technology is judged to obscure the gist of the present invention, the detailed description thereof will be omitted.

[0034] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used solely for the purpose of distinguishing one component from another.

[0035] Additionally, in the present application, a “part” may be a hardware component such as a processor or circuit, and / or a software component executed by a hardware component such as a processor.

[0036] Hereinafter, embodiments according to the present invention will be described in detail with reference to the attached drawings. In describing with reference to the attached drawings, identical or corresponding components are assigned the same drawing numbers, and redundant descriptions thereof will be omitted.

[0037] In the following examples, the terms first, second, etc. are not used in a limiting sense, but are used for the purpose of distinguishing one component from another.

[0038] In the examples below, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0039] In the following examples, terms such as “include” or “have” mean that a feature or component described in the specification is present, and do not preclude the possibility that one or more other features or components may be added.

[0040] In some embodiments, where the implementation is otherwise feasible, a particular process sequence may be performed in a different order than described. For example, two processes described in succession may be performed substantially simultaneously, or in a reverse order from the described order.

[0041]

[0042] FIG. 1 is a block diagram schematically illustrating the configuration of a device for automatically mapping an inverter of a solar module according to one embodiment. Referring to FIG. 1, a device (100) for automatically mapping an inverter of a solar module (hereinafter referred to as device (100)) may include a memory (110) and a processor (120).

[0043] The device (100) illustrated in FIG. 1 only shows components related to the present embodiments, and it is obvious to those skilled in the art that other general components may be included in addition to the components illustrated in FIG. 1.

[0044] For example, the device (100) may be implemented as various types of devices such as a notebook PC, a desktop PC, a laptop, a tablet computer, a mobile device including a smart phone, a server device, an embedded device, etc. As a specific example, the device (100) may correspond to a smart phone, a tablet device, an AR (Augmented Reality) device, an IoT (Internet of Things) device, an autonomous vehicle, etc. that perform voice recognition, image recognition, image classification, etc. using artificial intelligence, but is not limited thereto. Furthermore, the device (100) may include a dedicated hardware accelerator (HW accelerator) mounted on the above-mentioned devices, and the device (100) may include a hardware accelerator such as an NPU (neural processing unit), a TPU (Tensor Processing Unit), a Neural Engine, etc., which are dedicated modules for artificial intelligence operation, but is not limited thereto.

[0045] The memory (110) is hardware that stores various data processed within the device (100), and may include a computer-readable recording medium. For example, the memory (110) may store data processed and data to be processed within the device (100). In addition, the memory (110) may store applications, drivers, etc. to be driven by the device (100). The memory (110) may include at least one of volatile memory and nonvolatile memory. The volatile memory may include dynamic random access memory (DRAM), static random access memory (SRAM), synchronous dynamic random access memory (SDRAM), phase-change random access memory (PRAM), magnetic random access memory (MRAM), resistive random access memory (RRAM), ferroelectric random access memory (FeRAM), etc. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), electrically programmable read-only memory (EPROM), and electrically erasable programmable read-only memory (EEPROM).

[0046] In an embodiment, the memory (110) may include, but is not limited to, magnetic memory, CD-ROM, Blu-ray or other optical disk storage, hard disk drive (HDD), solid state drive (SSD), compact flash (CF), secure digital (SD), micro secure digital (Micro-SD), mini secure digital (Mini-SD), extreme digital (xD), or Memory Stick. In addition, the memory (110) may store an operating system and at least one program code (code for execution by a processor (120) operating with reference to FIGS. 2 to 6).

[0047] The processor (120) may serve to control the overall functions for executing the device (100) with reference to FIGS. 2 to 6. For example, the processor (120) may control at least one other component (e.g., hardware or software component) of an electronic device connected to the processor (120) by executing software (e.g., program) stored in the memory (110) within the device (100), and may perform various data processing or operations to control the device (100) as a whole.

[0048] For example, the processor (120) may receive a list of identification information of MLPE devices corresponding to each of a plurality of installed solar modules. The processor (120) may receive a first image including a plurality of first codes and an installed state of the solar modules, which are photographed using a drone. The processor (120) may calculate installation information related to the plurality of solar modules from the first image, and generate a first layout diagram based on the installation information. The processor (120) may recognize a plurality of first codes included in the first image, and obtain location information and identification information of a plurality of MLPE devices corresponding to the plurality of first codes. The processor (120) may generate a second layout diagram that modifies the first layout diagram by reflecting the location information and identification information of the plurality of MLPE devices.

[0049] When recognition of one or more of the plurality of first codes included in the first image is impossible, the processor (120) may move the drone to acquire one or more second images corresponding to the one or more first codes that are impossible to recognize, and may acquire location information and identification information of the plurality of MLPE devices based on the acquired second images. Specifically, the processor (120) may move the drone to be closer to one of the plurality of MLPE devices by a preset distance or less, capture and receive a plurality of second images including one or more of the plurality of first codes, and recognize the plurality of first codes included in the plurality of second images to acquire location information and identification information of the plurality of MLPE devices corresponding to the first codes.

[0050] Meanwhile, the processor (120) may compare the number of identification information of the micro inverter in the identification information list with the number of identification information corresponding to the plurality of recognized first codes, and if they do not match, may send an alarm and recommend location information on the first layout of the micro inverter corresponding to the unrecognized first code. In addition, the processor (120) may generate a second layout by modifying the first layout based on the recommended location information.

[0051] Meanwhile, the first code may be replaced with a second code corresponding to the identification information of the solar module. The processor (120) may construct a database (not shown) so that the identification information of the solar module corresponds to each of the identification information of the plurality of micro-inverters, and may correspond the first code to any one of the plurality of second codes based on the database.

[0052] According to one embodiment, the processor (120) may be implemented as a central processing unit (CPU), a graphics processing unit (GPU), an application processor (AP), a neural processing unit (NPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP) provided in the device (100), but is not limited thereto.

[0053]

[0054] Figure 2 is a flowchart illustrating a method for automatically mapping an inverter of a solar module according to one embodiment. In the following description, any portions that overlap with the description of Figure 1 will be omitted.

[0055] A solar power generation system (not shown) according to the present embodiment may refer to a power generation system that converts solar energy into electrical energy. The solar power generation system may include a plurality of photovoltaic (PV) modules, and each of the PV modules may include a Module Level Power Electronics (MLPE) device that converts the generated energy. The MLPE device may be an optimizer or a micro inverter. For example, when the MLPE device is an optimizer, the MLPE device may regulate power generated from the plurality of solar modules and output it to an inverter (e.g., a string inverter). The current converted by the inverter (e.g., converting direct current to alternating current) may be output to a load or a grid. As another example, when the MLPE device is a micro inverter, the MLPE device may convert power generated from the plurality of solar modules. The current converted by the MLPE device may be output to a load or a grid. For convenience of explanation, the following description will assume that the MLPE device is a micro inverter, but is not limited thereto.

[0056] A solar module is a module that generates electricity using the photovoltaic effect, and multiple solar modules can be interconnected to form a photovoltaic module array. The photovoltaic module array may be formed by connecting multiple solar modules in series or in parallel. In addition, the photovoltaic module array may include at least one photovoltaic module string. In one embodiment, when multiple solar modules are connected in series, the multiple solar modules can form a single photovoltaic module array through one photovoltaic module string. In another embodiment, when multiple solar modules are connected in parallel, the multiple solar modules can form a single photovoltaic module array through the multiple photovoltaic module strings.

[0057] Meanwhile, microinverters can be connected one-to-one to solar modules and convert the energy generated by the solar modules.

[0058] This embodiment will be described as an example of a solar power generation system including at least one solar module array.

[0059] A solar power generation system may include a plurality of solar module arrays, and the solar module array may include at least one solar module string comprising a plurality of solar modules. Therefore, each of the plurality of solar modules needs to be managed individually.

[0060] Accordingly, when installing or replacing solar modules to install a solar power generation system, the user can match the identification information of the solar module or the identification information of the micro-inverter with the location information where the solar module or micro-inverter is installed.

[0061] Referring to FIG. 2, in step S210, the processor (120) can receive a list of identification information of MLEP devices corresponding to each of the installed plurality of solar modules.

[0062] A solar power generation system may include multiple solar modules, and a micro-inverter, or MLEP device, may correspond one-to-one to a solar module.

[0063] The identification information list may refer to a list containing identification information of a microinverter installed in a solar power generation system. The identification information of the microinverter may include a serial number set when the microinverter is manufactured or shipped. Furthermore, according to one embodiment, the identification information of the microinverter may include an address, product number, etc. assigned to the microinverter. The identification information of the microinverter may be composed of a combination of letters, numbers, or symbols. Furthermore, the identification information of the microinverter may be set to exhibit regularity according to the installation location or layout structure of the microinverter.

[0064] Meanwhile, the processor (120) may receive information regarding the location where the solar power generation system is to be installed. For example, the processor (120) may receive information regarding the shape and size of the roof or rooftop of a building where the solar power generation system is to be installed, or the building's blueprint, and may calculate a possible location for installing the solar modules based on the received information. At this time, the processor (120) may calculate the optimal location where the solar power generation system generates the most power based on the information and performance of the solar modules and micro-inverters.

[0065] At step S220, a first image including a plurality of first codes and a state in which solar modules are installed can be received using a drone.

[0066] A first image including a plurality of first codes and a state in which solar modules are installed may include a plurality of zones, each of which may be used to indicate location information and identification information of a microinverter.

[0067] The first code may take the form of a one-dimensional (1D) code or a two-dimensional (2D) code. A one-dimensional (1D) code is a line-based code that may contain horizontally arranged information. A two-dimensional (2D) code is a square or rectangular code that may contain horizontally arranged information.

[0068] According to one embodiment, the first code may include a QR code (quick response code) in the form of a two-dimensional code, and the QR code may be used to indicate identification information of the micro inverter. Accordingly, the first code may include identification information such as the serial number and product number of the micro inverter, and the processor (120) may obtain identification information of the micro inverter corresponding to the first code by recognizing or scanning the first code.

[0069] Meanwhile, the first code is not limited to a two-dimensional code, and may be a one-dimensional code in the form of a barcode or another form of identifier code. However, for the convenience of explanation, the first code will be described below in the form of a QR code.

[0070] The processor (120) may obtain a first image including a first code by a process of photographing or scanning using a drone according to one embodiment, and may also obtain the first image by direct input from a user according to another embodiment.

[0071] When installing a solar power generation system, a user (or installer) may use a drone to capture or scan a first image to obtain a first code containing identification information of a microinverter. Specifically, when installing a microinverter, the user (or installer) may use a drone to capture or scan multiple microinverters with the first code attached, thereby obtaining a first image containing the first code, without having to remove the first code attached to the microinverter and attach it to a paper template. Accordingly, the first image containing the first code may not be a physical photograph in the strict sense, but may include a form that may include location information and identification information.

[0072] In step S230, the processor (120) can derive installation information related to the solar module from the first image and generate a first layout drawing based on the installation information.

[0073] The processor (120) may receive a first image including a state in which a plurality of solar modules are installed, which is photographed using a drone. In the present embodiment, the first image may include metadata following the Exif (Exchangeable image file format) format. The metadata may include information on the date and time the first image was photographed, information on the model and manufacturer of the camera used, information on the resolution and size of the first image, GPS information including the latitude, longitude, and altitude of the photographing location for the first image, and information on photographing conditions such as the aperture value, shutter speed, and ISO when the first image was photographed. In addition, the first image may include center coordinates of the solar module or relative position information based on a specific point so as to identify the position and direction of the solar module. In addition, the first image may include environmental elements around the solar module, such as surrounding buildings, trees, and the ground.

[0074] Meanwhile, the processor (120) can derive installation information related to a plurality of solar modules from the first image. In the present embodiment, the installation information may include tilt angles and azimuth angles for the plurality of solar modules.

[0075] In the present embodiment, when calculating installation information, the processor (120) may receive a first image from the drone along with tilt angles and azimuth angles for a plurality of solar modules included in the first image. The drone is equipped with an acceleration sensor (not shown) and a gyroscope sensor (not shown), and the processor (120) may calculate tilt angles and azimuth angles for a plurality of solar modules corresponding to the first image. The processor (120) may determine the tilt angles and azimuth angles for a plurality of solar modules received from the drone as installation information.

[0076] As an optional example, the processor (120) can apply image analysis techniques to the first image to derive tilt angles and azimuth angles for a plurality of solar modules from the first image.

[0077] The processor (120) can detect a roof and a ground from a first image and calculate a tilt angle as a slope of the roof relative to the ground. The processor (120) can use color-based segmentation and boundary detection among image processing and vision technologies to extract the roof and the ground from the first image. Since the roof and the ground generally have different colors or brightnesses, the processor (120) can segment the first image based on color information to separate the roof and the ground areas. Using the HSV (hue, saturation, value) color space, a specific range of colors can be selected and extracted. For example, since roofs are generally gray or brown, the corresponding color range can be selected and separated. The boundary between the roof and the ground can be detected using Canny edge detection or other boundary detection algorithms. Since the boundaries will have different patterns, the roof and the ground can be separated through this. The processor (120) can calculate a tilt angle as a slope of the roof relative to the ground using the separated roof and ground.

[0078] The processor (120) can calculate an azimuth based on information included in the metadata of the first image and a tilt angle. Information included in the metadata used to calculate the azimuth may include information on the date and time the first image was captured, and GPS information including the latitude, longitude, and altitude of the capture location for the first image. The processor (120) can calculate the solar hour angle from the information on the date and time the first image was captured, and calculate the latitude of the installation location of the solar module from the GPS information of the first image. The processor (120) can calculate the azimuth of a plurality of solar modules by the following mathematical expression 1.

[0079]

[0080] In mathematical equation 1, indicates the latitude of the solar module installation location, is the hour angle of the sun, can represent the tilt angle described above.

[0081] The processor (120) can determine the calculated tilt angle and azimuth angle as installation information related to a plurality of solar modules.

[0082] As an optional example, when generating installation information, the processor (120) may generate installation information related to a plurality of solar modules corresponding to a first image using a deep neural network model that is pre-trained to generate installation information related to a plurality of solar modules corresponding to an image including a state in which a plurality of solar modules are installed. Here, the deep neural network model may be a model trained in a supervised learning manner using training data that inputs an image including a state in which a plurality of solar modules are installed and labels the tilt angle and azimuth angle of the solar modules.

[0083] The processor (120) can train an initially set deep neural network model using a supervised learning method using labeled training data. Here, the initially set deep neural network model is an initial model designed to be configured as a model capable of generating installation information related to a plurality of solar modules in response to an image including a state in which a plurality of solar modules are installed, and the parameter values ​​may be set to arbitrary initial values. The initial model may be completed as a generation model capable of accurately generating installation information related to a plurality of solar modules in response to an image including a state in which a plurality of solar modules are installed by optimizing the parameter values ​​while being trained using the above-described training data.

[0084] As an optional example, the processor (120) can load a solar installation drawing (CAD drawing) that must be submitted when installing a solar module, and calculate a tilt angle and an azimuth angle from the solar installation drawing.

[0085] Typically, when installing solar modules, solar installation drawings may be submitted to government agencies to ensure compliance with local building codes and solar power generation regulations. Solar installation drawings may include information such as the installation location and orientation of solar modules, electrical connections and wiring, structural elements of supports used during installation, and the relative positions and connections of solar modules and micro-inverters. The installation location and orientation of solar modules may include information on the installation direction and inclination of the solar modules. The processor (120) may extract the installation direction and inclination information of the solar modules from the solar installation drawings, and determine the extracted installation direction and inclination information as azimuth and tilt angle, respectively.

[0086] Meanwhile, the processor (120) may generate a first layout including a plurality of zones divided in a table format based on the first image. For example, rows within the table may be represented by numeric indices in the form of 1, 2, 3, 쪋, respectively, and columns within the table may be represented by English indices in the form of A, B, C, 쪋, respectively. Accordingly, in this case, any cell within the table may be represented using row indices and column indices, and a zone within the first row and first column within the table may be represented as A1.

[0087] In step S240, the processor (120) can recognize the first code and obtain location information and identification information of a plurality of MLEP devices corresponding to the plurality of first codes.

[0088] The processor (120) can identify coordinate information of an area where a micro inverter with a first code attached is installed from the input first image, and can obtain location information of the micro inverter using the coordinate information. For example, if the processor (120) obtains a first image in which a micro inverter is installed in an area within a first row and a first column and a first code is attached to the micro inverter, a first layout diagram in the form of a table consisting of one row and one column can be generated. At this time, the coordinate information of the installation area of ​​the micro inverter with the first code attached can be A1, and the processor (120) can correspond A1, which is coordinate information of the area, to the location information of the first code.

[0089] In step S250, the processor (120) can generate a second layout plan that modifies the first layout plan by reflecting the location information and identification information of the acquired plurality of MLEP devices.

[0090] According to one embodiment, the processor (120) may generate a second layout by arranging a first code in the first layout to correspond to location information, and in addition to the first code, may arrange identification information of the micro-inverter or real-time power generation information of the solar module corresponding to the micro-inverter. The processor (120) may receive power generation information through a controller that is attached to or connected to the solar module and can control or monitor the solar panel. Here, the power generation information may include voltage, current, power generation amount, temperature, defects, etc. of the solar module, and the controller may include a communication module that can transmit the monitored information to an external device.

[0091] Meanwhile, when the calculation of the tilt angle and azimuth angle of the solar module is completed, the processor (120) can generate a second layout plan by modifying the first layout plan of the micro inverter based on the installation information including the tilt angle and azimuth angle of the solar module, and output the second layout plan to the user's terminal. Here, modifying the first layout plan may include rotating the second layout plan based on the tilt angle and azimuth angle. Accordingly, the processor (120) can generate a modification result of the first layout plan by rotating the first layout plan based on the tilt angle and azimuth angle included in the installation information, and determine the modification result of the first layout plan as the second layout plan.

[0092] In the present embodiment, the processor (120) may record installation information including the tilt angle and azimuth angle of the solar module in a second layout diagram of the micro inverter, and output the second layout diagram of the micro inverter, in which the installation information including the tilt angle and azimuth angle of the solar module is recorded, to the user's terminal. In another embodiment, the processor (120) may record installation information including the tilt angle and azimuth angle of the solar module outside the second layout diagram, and output the second layout diagram and the installation information including the tilt angle and azimuth angle of the solar module to the user's terminal.

[0093] As an optional embodiment, the processor (120) may record the tilt angle and azimuth angle of the solar module in a first layout diagram of the micro inverter, and output the first layout diagram of the micro inverter, in which the tilt angle and azimuth angle of the solar module are recorded, to a user's terminal. As another embodiment, the processor (120) may record installation information including the tilt angle and azimuth angle of the solar module outside the first layout diagram, and output the first layout diagram and the installation information including the tilt angle and azimuth angle of the solar module to the user's terminal.

[0094] According to one embodiment, when the processor (120) places the first code to generate the second layout, the user can check the layout status of the micro inverter through the second layout within the application of the user terminal, and by touching the first code on the second layout, the user can check detailed information about the status or power generation information of the micro inverter and solar module corresponding to the first code.

[0095] According to another embodiment, when the processor (120) generates a second layout by arranging real-time power generation information, the user can check the layout status of the micro-inverter through the second layout within the application of the user terminal, and can check the status or power generation information of the solar module corresponding to the micro-inverter at a glance in a simplified form.

[0096] The user can change the position of the first code in the second layout using drag and drop, and the processor (120) can generate the second layout by reflecting the position information of the micro inverter changed by the user's drag and drop input.

[0097] As an optional example, the processor (120) may compare the number of identification information of the micro inverter in the identification information list with the number of identification information corresponding to the plurality of recognized first codes, and if they do not match, may send an alarm and recommend location information on the second layout of the micro inverter corresponding to the unrecognized first code.

[0098] Specifically, the processor (120) may compare the number of pieces of identification information of the micro-inverter in the identification information list of the micro-inverter received in step S210 with the number of pieces of identification information of the first code recognized in step S240. If the comparison result does not match, this may include a case where the first code is not recognized by the processor (120) or the first code is removed from the micro-inverter due to a mistake by the user (or installer). In this case, the processor (120) may send an alarm to the user regarding the unrecognized or removed first code, and may recommend location information of the micro-inverter corresponding to the unrecognized or removed first code to the user.

[0099] The processor (120) can calculate the location information to which the first code should correspond based on the first layout diagram generated in step S230. For example, if the first layout diagram is generated when it is recognized that a micro-inverter is installed, and if the first layout diagram requires a first code to correspond to a first location information but there is no corresponding first code, the processor (120) can recommend the first location information as the location information of the micro-inverter corresponding to the unrecognized or removed first code.

[0100] If there is only one unrecognized or removed first code, the processor (120) may skip the process of sending an alarm and recommending location information for the unrecognized or removed first code, and then input the first location information into the location information of the micro inverter corresponding to the unrecognized or removed first code. In addition, the processor (120) may output a second layout diagram generated based on the input first location information to the user terminal, and may express that the first location information has been input to the first code by applying a different color, blinking, emphasis, or other expression to the second layout diagram for the unrecognized or removed first code.

[0101] If there are two or more unrecognized or removed first codes, there may be multiple pieces of first location information that must correspond to a first code but do not have a corresponding first code, and the processor (120) may recommend multiple pieces of first location information to the user for the location information of the micro inverter corresponding to the unrecognized or removed first codes, and input the first location information selected by the user as the location information of the micro inverter. If there is any remaining first location information that has not been selected by the user, the processor (120) may input the remaining first location information into the first code for which the location information has not been input, without the user's selection, to generate a second layout.

[0102] Additionally, the processor (120) can modify the first layout based on the recommended location information to generate a second layout.

[0103] In this embodiment, the first code may be replaced with the second code, and the processor (120) may receive a first image from a user or a drone in which some of the first codes are replaced with the second code, or may receive a first image in which all of the first codes are replaced with the second code.

[0104] The second code may be in the form of a one-dimensional or two-dimensional code. A one-dimensional code (1D barcode) is a code consisting of lines that can represent information horizontally. A two-dimensional code (2D barcode) is a square or rectangular code that can represent information both horizontally and vertically.

[0105] According to one embodiment, the second code may include a barcode in the form of a one-dimensional code, and the barcode may be used to indicate identification information of the solar module. Accordingly, the second code may include identification information such as the serial number or product number of the solar module, and the processor (120) may obtain identification information of the solar module corresponding to the second code by recognizing or scanning the second code.

[0106] Meanwhile, the second code is not limited to a one-dimensional code, and may be a two-dimensional code in the form of a QR code or another form of identifier symbol, but for the convenience of explanation, the second code will be described below in the form of a barcode.

[0107] The processor (120) may obtain the first image including the second code by a process of photographing or scanning using a drone according to one embodiment, and may obtain the first image including the second code by direct input from a user according to another embodiment.

[0108] Since a micro-inverter can correspond one-to-one to a solar module, the first code including the identification information of the micro-inverter can be replaced with a second code including the identification information of the solar module. In addition, the processor (120) can obtain the identification information of the solar module corresponding to each piece of identification information of the micro-inverter from a preset database. According to another embodiment, the processor (120) can build a database for one-to-one correspondence between the identification information of the micro-inverter and the identification information of the solar module. Therefore, if the identification information of the micro-inverter is lost or cannot be recognized, the user can use a drone to photograph or scan the solar module to which the second code is attached, and the processor (120) can obtain the first code corresponding to the second code using the preset database. In other words, the processor (120) can obtain the identification information of the micro-inverter corresponding to the identification information of the solar module using the database.

[0109]

[0110] Figures 3a and 3b are exemplary diagrams of a first image captured using a drone according to one embodiment. In the following description, any portions that overlap with the descriptions of Figures 1 and 2 will be omitted.

[0111] Referring to FIGS. 3A and 3B , the processor (120) may receive a first image (1001) including a plurality of first codes (501) photographed at a distance d1 using a drone (310) and a state in which a solar module is installed. In this case, d1 may refer to a straight-line distance between any one of the plurality of MLPE devices and the drone (310). In the present embodiment, the first image (1001) may include metadata including information on the shooting date and time, and GPS information including latitude, longitude, and altitude of the shooting location. In addition, the first image (1001) may include center coordinates of the solar module or relative location information based on a specific point so as to identify the location and direction of the solar module. In addition, the first image (1001) may include environmental elements around the solar module, such as surrounding buildings, trees, and the ground.

[0112]

[0113] Figures 4a and 4b are examples of second images captured using a drone according to one embodiment. In the following description, any portions that overlap with the descriptions of Figures 1 to 3b will be omitted.

[0114] Referring to FIGS. 4A and 4B , the processor (120) may receive a second image (1002) including a plurality of first codes (501) photographed at a distance d2 using the drone (310) and a state in which solar modules are installed. Specifically, if the processor (120) cannot recognize one or more of the plurality of first codes (501) included in the first image (1001), the processor (120) may move the drone closer to one of the plurality of micro inverters within a preset distance to capture the second image (1002). In this case, d2 may mean a straight-line distance between one of the plurality of MLPE devices and the drone (310), and may mean a distance shorter than d1.

[0115]

[0116] Figures 5a and 5b are exemplary diagrams illustrating the generation of installation information from a first image according to one embodiment. In the following description, any portions that overlap with the descriptions of Figures 1 to 4b will be omitted.

[0117] Referring to FIGS. 5A and 5B, the processor (120) can generate installation information including tilt angles and azimuth angles for a plurality of solar modules based on the first image (1001).

[0118] FIG. 5A illustrates a method for calculating a tilt angle for a plurality of solar modules. Referring to FIG. 5A, the processor (120) can detect a roof (1101) and a ground (1102) from a first image (1001) using color-based segmentation and boundary detection among image processing and vision technologies. Since the roof (roof surface) (1101) and the ground (1102) generally have different colors or brightnesses, the processor (120) can segment the first image (1001) based on color information to separate the roof and ground areas. In addition, the processor (120) can detect the boundary between the roof (1101) and the ground (1102) using Canny edge detection or other boundary detection algorithms. Since the boundaries will have different patterns, the roof (1101) and the ground (1102) can be separated through this. The processor (120) uses a separated roof (1101) and ground (1102) to calculate the tilt angle as an inclination of the roof (1101) relative to the ground (1102). ) can be produced.

[0119] FIG. 5b illustrates a method for calculating an azimuth for a plurality of solar modules. Referring to FIG. 5b, the processor (120) can draw a virtual line from the center (O) of the roof surface (1101) to the center of the south-facing side (1103) of the roof surface (1101), and calculate the azimuth as the angle measured in the clockwise (west) direction from the due south direction to the virtual line. If the virtual line is located in the counterclockwise (east) direction from the due south direction, the measured angle can be expressed as a negative number (-). If the azimuth (α) is negative (-), it means that the south-facing side (1103) of the roof surface (1101) is turned from the south toward the east, and this is illustrated in FIG. 5b. Conversely, if the azimuth (α) is positive (+), it can mean that the south-facing side (1103) of the roof surface (1101) is turned from the south toward the west.

[0120] As an optional example, the processor (120) calculates the azimuth (α) by calculating the date and time information of the first image (1001) included in the metadata of the first image (1001) when the first image (1001) was taken, the GPS information including the latitude, longitude and altitude of the shooting location for the first image (1001) and the tilt angle (α) calculated with reference to FIG. 5a. ) can be used. The processor (120) obtains the sun's hour angle ( ) and the latitude (of the installation location of the solar module) is calculated from the GPS information of the second image (1001). ) can be calculated. The processor (120) can calculate the azimuth (α) of a plurality of solar modules by the above-described mathematical expression 1. In the present embodiment, the azimuth is a concept indicating a relative direction, and simply indicates where an object or location is, and the azimuth may include a concept of accurately indicating the direction of an object in degrees based on a specific axis.

[0121] As an example, the processor (120) may receive a tilt angle and an azimuth angle for a plurality of solar modules included in the first image (1001) together with a second image (1001) from the user's terminal.

[0122] In another embodiment, when generating installation information, the processor (120) may generate installation information related to a plurality of solar modules corresponding to a first image using a deep neural network model that is pre-trained to generate installation information related to a plurality of solar modules corresponding to an image including a state in which a plurality of solar modules are installed. Here, the deep neural network model may be a model trained in a supervised learning manner using training data that inputs an image including a state in which a plurality of solar modules are installed and labels the tilt angle and azimuth angle of the solar modules.

[0123]

[0124] Figure 6 is an exemplary diagram illustrating a process for outputting a second layout diagram based on installation information according to one embodiment. In the following description, any portions that overlap with the descriptions of Figures 1 to 5 will be omitted.

[0125] Referring to FIG. 6, the processor (120) may receive a first image (1001) taken using a drone using the user terminal (401). In addition, the processor (120) may receive a second image (301) including a first code taken using the drone through an application in the user terminal (401). According to one embodiment, the application in the user terminal (401) is displayed on the display interface of the user terminal (401), and an icon corresponding to a function of receiving or taking pictures may be displayed on the user interface of the application displayed in the user terminal (401). For example, the user may touch a photo album icon corresponding to a function of inputting images in order to input a first image (1001) and a second image (1002) including a plurality of first codes into the user terminal (401), and the user terminal (401) may display images stored therein. When a user selects a first image (1001) or a second image (1002) including a first code among the displayed images, the processor (120) can obtain the first image (1001) or the second image (1002) including a plurality of first codes selected by the user. In another embodiment, the user can touch a camera icon corresponding to a function of taking an image to take a picture of the first image (1001) and the second image (1002) including a plurality of first codes using the drone (310), and the user terminal (401) can control the drone (310) to take an image with a camera mounted on the drone (310) to obtain the first image (1001) and the second image (1002) including a plurality of first codes.

[0126] The processor (120) can derive installation information including a tilt angle and an azimuth angle from the first image (1001) and / or the second image (1002). The processor (120) can generate a first layout diagram (1101) of the micro inverter based on the installation information including the tilt angle and azimuth angle of the solar module and output it to the user's terminal.

[0127] The processor (120) can record installation information including the tilt angle and azimuth angle of the solar module in the first layout diagram (1101) of the micro inverter and output the first layout diagram (1101) to the user's terminal (401). In another embodiment, the processor (120) can record installation information including the tilt angle and azimuth angle of the solar module on the outside of the first layout diagram (1101) and output the first layout diagram (1101) and the installation information including the tilt angle and azimuth angle of the solar module to the user's terminal.

[0128] The processor (120) can recognize a plurality of first codes (301) included in the first image (1001) and / or the second image (1002), and can reflect the recognized plurality of first codes (301) in the first layout (1101) to generate a second layout (402).

[0129] As an optional embodiment, the processor (120) may record the tilt angle and azimuth angle of the solar module in the second layout diagram (402) of the micro inverter, and output the second layout diagram (402) of the micro inverter, in which the tilt angle and azimuth angle of the solar module are recorded, to the user's terminal (401). As another embodiment, the processor (120) may record installation information including the tilt angle and azimuth angle of the solar module on the outside of the second layout diagram (402), and output the second layout diagram (402) and the installation information including the tilt angle and azimuth angle of the solar module to the user's terminal (401).

[0130] Meanwhile, when the processor (120) acquires a first image (1001) including a plurality of first codes, the processor (120) can recognize the first code and acquire location information and identification information of the micro inverter corresponding to the first code. The processor (120) can generate a second layout diagram (402) by modifying the first layout diagram (1101) of the micro inverter by reflecting the acquired location information and identification information, and output the second layout diagram (402) of the micro inverter to the user interface of the application in the user terminal (401). Meanwhile, when there is no first code arranged in a column or row of the second layout diagram (402), the processor (120) can generate and output the second layout diagram (402) in a form in which the corresponding column or row is omitted.

[0131] Meanwhile, if the processor (120) is unable to recognize the first code included in the first image (1001), the processor (120) may move the drone closer to the micro inverter. At this time, the processor (120) may move the drone closer to the area where the micro inverter exists based on the first layout (1101) to capture a plurality of second images including the first code. In response to receiving the plurality of second images, the processor (120) may recognize the first code included in the plurality of second images to obtain location information and identification information of the micro inverter corresponding to the first code.

[0132] Meanwhile, the drone may include a thermal imaging camera, and the processor (120) may use the thermal imaging camera of the drone equipped with a thermal infrared sensor to determine whether a problem has occurred in the micro-inverter. Specifically, if the processor (120) analyzes the first image captured by the thermal imaging camera of the drone and determines that the temperature of the micro-inverter is above or below a predetermined temperature, the processor may determine that the micro-inverter is malfunctioning or cannot operate normally due to foreign matter, and may send a notification to the user regarding the occurrence of a problem.

[0133] For example, if the processor (120) analyzes that the first image taken using a drone equipped with a thermal detection camera contains a micro-inverter that is heating at 55°C or higher or 10°C or lower, the processor (120) can analyze the first image to determine whether a foreign substance is attached to the outside of the micro-inverter. If the processor (120) determines that a foreign substance is attached to the outside of the micro-inverter as a result of analyzing the first image, the processor (120) can control the drone to remove the foreign substance. For example, if the drone is equipped with a fan, the foreign substance can be removed using the wind generated by operating the fan, or if the drone is not equipped with a fan, the foreign substance can be removed using the wind generated by the operation of the drone. Alternatively, if the drone is equipped with a storage container capable of holding a small amount of water and a sprayer capable of spraying the water contained in the storage container, the processor (120) can control the sprayer to remove the foreign substance. If the processor (120) determines that no foreign substance is attached to the outside of the micro inverter as a result of analyzing the first image, the processor (120) determines that a failure has occurred in the micro inverter and can send a notification to the user regarding the failure.

[0134]

[0135] The embodiments of the present invention described above may be implemented in the form of a computer program that can be executed through various components on a computer, and such a computer program may be recorded on a computer-readable medium. At this time, the medium may include a magnetic medium such as a hard disk, a floppy disk, and a magnetic tape, an optical recording medium such as a CD-ROM and a DVD, a magneto-optical medium such as a floptical disk, and a hardware device specifically configured to store and execute program instructions, such as a ROM, a RAM, a flash memory, etc.

[0136] Meanwhile, the computer program may be specifically designed and constructed for the present invention, or may be one known and available to those skilled in the computer software field. Examples of computer programs may include not only machine language code, such as that generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

[0137] The use of the term "above" and similar referential terms in the specification of the present invention (especially in the claims) may refer to both singular and plural. Furthermore, when a range is described in the present invention, it is intended that the invention encompasses inventions that apply individual values ​​falling within the range (unless otherwise stated), and is equivalent to describing each individual value constituting the range in the detailed description of the invention.

[0138] Unless the steps constituting the method according to the present invention are explicitly described in a specific order or are not described to the contrary, the steps may be performed in any appropriate order. The present invention is not necessarily limited to the order in which the steps are described. The use of all examples or exemplary terms (e.g., "for example," etc.) in the present invention is merely intended to illustrate the present invention in detail, and the scope of the present invention is not limited by the examples or exemplary terms unless otherwise defined by the claims. Furthermore, those skilled in the art will appreciate that various modifications, combinations, and variations can be configured according to design conditions and factors within the scope of the appended claims or their equivalents.

[0139] Therefore, the idea of ​​the present invention should not be limited to the embodiments described above, and all scopes equivalent to or equivalently modified from the following claims as well as the claims are considered to fall within the scope of the idea of ​​the present invention.

Claims

1. A step of receiving a list of identification information of MLPE (Module Level Power Electronics) devices corresponding to each of a plurality of installed solar modules; A step of receiving a first image including a plurality of first codes photographed using a drone and a state in which the solar module is installed; A step of calculating installation information related to the plurality of solar modules from the first image and generating a first layout drawing based on the installation information; A step of recognizing the plurality of first codes included in the first image and obtaining location information and identification information of the plurality of MLPE devices corresponding to the plurality of first codes; and A step of generating a second layout by modifying the first layout by reflecting the location information and identification information of the plurality of MLPE devices obtained above; The above acquisition steps are: A step of moving the drone to acquire one or more second images corresponding to one or more of the first codes that cannot be recognized, and acquiring location information and identification information of the plurality of MLPE devices based on the acquired second images, when one or more of the plurality of first codes included in the first image cannot be recognized; A method for automatically mapping an inverter of a solar module, comprising:

2. In paragraph 1, The above acquisition steps are: A step of moving the drone so as to be closer to one of the plurality of MLPE devices within a preset distance, capturing and receiving a plurality of second images including at least one of the plurality of first codes, and recognizing the plurality of first codes included in the plurality of second images to obtain location information and identification information of the plurality of MLPE devices corresponding to the first codes; A method comprising:

3. In paragraph 1, The above acquisition steps are: A step of recognizing the first code included in the first image, identifying coordinate information of the first code, and obtaining location information of the micro inverter using the coordinate information; A method comprising:

4. In paragraph 1, The step of generating the above first layout diagram is: A step of receiving a tilt angle and an azimuth measured corresponding to the first image by an acceleration sensor and a gyroscope sensor provided in the drone; and A step of determining the above tilt angle and azimuth angle as installation information related to the plurality of solar modules; A method comprising:

5. In paragraph 1, The step of generating the above first layout diagram is: A step of extracting a roof and a ground on which the plurality of solar modules are installed from the first image, and calculating a tilt angle as an inclination of the roof relative to the ground; A step of calculating the azimuth of the plurality of solar modules based on the information included in the metadata of the first image and the tilt angle; and A step of determining the tilt angle and the azimuth angle as installation information related to the plurality of solar modules; A method comprising:

6. In paragraph 1, The step of generating the above first layout diagram is: A step of generating installation information related to the plurality of solar modules corresponding to the first image using a deep neural network model that is pre-trained to generate installation information related to the plurality of solar modules corresponding to the first image including a state in which the plurality of solar modules are installed; including; The above deep neural network model is, A method for training a model using a supervised learning method using the first image including the state in which the plurality of solar modules are installed as input and training data having the tilt angle and azimuth angle of the solar modules as labels.

7. In paragraph 1, The step of generating the above first layout diagram is: A step of loading a solar installation drawing generated when installing the above plurality of solar modules; A step of extracting the tilt angle and azimuth included in the above solar power installation drawing; and A step of determining the above tilt angle and azimuth angle as installation information related to the plurality of solar modules; A method comprising:

8. In paragraph 1, The step of generating the above second layout diagram is: A step of generating a modified result of the first layout plan by modifying the first layout plan based on the tilt angle and azimuth included in the above installation information; and A step of determining the result of modifying the first layout as the second layout; A method comprising:

9. A computer-readable recording medium storing a computer program for executing any one of the methods of clauses 1 to 7 using a computer.

10. At least one processor; and Contains at least one memory, At least one processor, Receive a list of identification information of MLPE (Module Level Power Electronics) devices corresponding to each of the installed multiple solar modules, Receive a first image including a plurality of first codes photographed using a drone and a state in which the solar modules are installed, From the first image, installation information related to the plurality of solar modules is derived, and a first layout drawing is created based on the installation information, Recognizing the plurality of first codes included in the first image and obtaining location information and identification information of the plurality of MLPE devices corresponding to the plurality of first codes, It is configured to generate a second layout plan that modifies the first layout plan by reflecting the location information and identification information of the plurality of MLPE devices obtained above, At least one processor, A device for automatically mapping an inverter of a solar module, configured to move the drone to acquire one or more second images corresponding to one or more of the first codes that cannot be recognized when recognition of any one or more of the plurality of first codes included in the first image is impossible, and to acquire location information and identification information of the plurality of MLPE devices based on the acquired second images.

11. In paragraph 10, At least one processor, A device that moves the drone closer to one of the plurality of MLPE devices to a preset distance or less, captures and receives a plurality of second images including at least one of the plurality of first codes, and recognizes the plurality of first codes included in the plurality of second images to obtain location information and identification information of the plurality of MLPE devices corresponding to the first codes.

12. In paragraph 10, At least one processor, A device configured to, when acquiring location information and identification information of the micro inverter, recognize the first code included in the first image, identify coordinate information of the first code, and acquire location information of the micro inverter using the coordinate information.

13. In paragraph 10, At least one processor, When generating the first layout, the tilt angle and azimuth measured corresponding to the first image are received by the acceleration sensor and gyroscope sensor provided in the drone, A device configured to determine the tilt angle and azimuth angle using installation information related to the plurality of solar modules.

14. In paragraph 10, At least one processor, When generating the first layout, the roof and the ground are extracted from the first image, and a tilt angle as an inclination of the roof relative to the ground is calculated, The latitude of the installation location of the solar module is obtained from the GPS information included in the first image, the solar hour angle is obtained from the shooting date and shooting time included in the first image, and the azimuth is calculated based on the tilt angle. A device configured to determine the tilt angle and the azimuth angle using installation information related to the plurality of solar modules.

15. In paragraph 10, At least one processor, When generating the first layout, a deep neural network model that is pre-trained to generate installation information related to a plurality of solar modules corresponding to the first image including a state in which a plurality of solar modules are installed is used to generate installation information related to the plurality of solar modules corresponding to the first image, The above deep neural network model is, A device that is a model trained in a supervised learning manner using training data that inputs the first image including the state in which the plurality of solar modules are installed and labels the tilt angle and azimuth angle of the solar modules.

16. In paragraph 10, At least one processor, When generating the above first layout drawing, load the solar installation drawing generated when installing the plurality of solar modules, Extract the tilt angle and azimuth included in the above solar power installation drawing, A device configured to determine the tilt angle and azimuth angle using installation information related to the plurality of solar modules.

17. In paragraph 10, At least one processor, When generating the second layout, a result of modifying the first layout is generated by modifying the first layout based on the tilt angle and azimuth included in the installation information, A device configured to determine the result of modification of the first layout as the second layout.

Images