Digital twin model-based system and method for predicting power generation amount of photovoltaic power station

Abstract

Provided is a digital twin model-based method for predicting the power generation amount of a photovoltaic power station. The method includes the steps of: acquiring location information and weather information of a photovoltaic power station; generating a digital twin model for cloud movement simulation based on information of a region in which the photovoltaic power station is located and a weather condition corresponding to the information of the region; modeling cloud movement information by inputting regional weather pattern information to the digital twin model; acquiring future time-based solar irradiance prediction information by inputting the modeled cloud movement information into a pre-trained artificial intelligence model; and predicting the amount of power generation of the photovoltaic power station by calculating thermal information of a photovoltaic panel corresponding to the solar irradiance prediction information.

Description

System and method for predicting power generation of solar power plants based on digital twin models

[0001] The present invention relates to a system and method for predicting power generation of a solar power plant based on a digital twin model.

[0002] Digital twins are a technology that accurately models real-world physical objects or systems to create a virtual twin (environment) in digital space. The goal is to monitor and optimize objects or processes in real time. This technology is often combined with modern technologies such as the Internet of Things (IoT), artificial intelligence (AI), and big data, and is bringing about innovative changes across various industries.

[0003] Digital twins can accurately model physical objects or systems digitally, allowing them to replicate real-world physical characteristics and behaviors in a digital environment. Furthermore, by updating the status, behavior, and performance of objects or processes in real time, digital twins can accurately reflect changes in the real world.

[0004] In addition, it is used in conjunction with Internet of Things technology to connect various physical objects in the real world, enabling monitoring of physical systems in the real world and rapid detection and action when problems occur.

[0005] These digital twin technologies are contributing to more efficient operation of complex real-world systems and problem prevention, and there is a need for technologies that can improve power generation predictions at solar power plants by applying these digital twin technologies.

[0006] An embodiment of the present invention provides a system and method for predicting power generation of a solar power plant based on a digital twin model, which recognizes a cloud object in an image captured by a sky camera using digital twin technology, models movement information of the recognized cloud object, and predicts future power generation of the solar power plant.

[0007] However, the technical task that this embodiment seeks to achieve is not limited to the technical task described above, and other technical tasks may exist.

[0008] As a technical means for achieving the above-described technical task, a method for predicting power generation of a solar power plant based on a digital twin model according to a first aspect of the present invention includes the steps of: obtaining location information and weather information of a solar power plant; generating a digital twin model for simulating cloud movement based on regional information where the solar power plant is located and weather conditions corresponding to the regional information; inputting regional weather pattern information into the digital twin model to model cloud movement information; inputting the modeled cloud movement information into a pre-learned artificial intelligence model to obtain solar irradiance prediction information for each future time zone; and calculating thermal information of a solar panel corresponding to the solar irradiance prediction information to predict the power generation of the solar power plant.

[0009] In some embodiments of the present invention, the step of obtaining location information and weather information of the solar power plant may include the step of capturing a sky image corresponding to the solar power plant based on a sky camera installed in the solar power plant; and the step of recognizing a cloud image included in the sky image as object information and obtaining it as the weather information.

[0010] In some embodiments of the present invention, the step of recognizing a cloud image included in the sky image as object information and obtaining the weather information may include recognizing object information including the shape, movement direction, and thickness of the cloud image and obtaining the weather information.

[0011] In some embodiments of the present invention, the step of generating a digital twin model for simulating cloud movement based on regional information where the solar power plant is located and weather conditions corresponding to the regional information may generate the digital twin model by further reflecting real-time performance data of each solar panel.

[0012] Some embodiments of the present invention may further include a step of dynamically adjusting the optimal arrangement of the solar panels based on the predicted power generation amount of the solar power plant.

[0013] In addition, a system for predicting power generation of a solar power plant through cloud movement prediction based on digital twins according to a second aspect of the present invention includes a communication unit for obtaining location information and weather information of a solar power plant, a memory storing a program for generating a digital twin model and predicting power generation of a solar power plant based on the digital twin model, and a processor for executing the program stored in the memory to generate a digital twin model for simulating cloud movement based on regional information where the solar power plant is located and meteorological conditions corresponding to the regional information, inputting regional weather pattern information into the digital twin model to model cloud movement information, inputting the modeled cloud movement information into a pre-learned artificial intelligence model to obtain solar irradiance prediction information for each time zone in the future, and then calculating thermal information of a solar panel corresponding to the solar irradiance prediction information to predict power generation of the solar power plant.

[0014] In some embodiments of the present invention, the processor may further reflect real-time performance data of each solar panel to generate the digital twin model.

[0015] In some embodiments of the present invention, the processor can dynamically adjust the optimal arrangement of the solar panels based on the predicted power generation amount of the solar power plant.

[0016] In addition, other methods for implementing the present invention, other systems, and computer-readable recording media recording a computer program for executing the above methods may be further provided.

[0017] According to one embodiment of the present invention described above, the shape and movement of clouds generated by a solar power plant can be reflected in a digital twin platform using a sky camera, enabling efficient prediction and optimization of the power generation of the solar power plant. This can lead to numerous benefits, including improved power generation prediction accuracy, the possibility of optimal deployment and operation, and increased energy efficiency.

[0018] Specifically, cloud movement prediction analyzes cloud images captured by a sky camera and transmits them to a digital twin platform, and based on this, the direction of cloud movement is simulated, the amount of solar radiation reaching solar panels is accurately predicted, and the amount of power generation can be predicted more accurately.

[0019] Additionally, by utilizing cloud movement information, an optimal placement algorithm based on digital twins can be introduced, which can be used to adjust the placement of solar panels to enable dynamic structural operation that can accommodate maximum solar irradiance.

[0020] Additionally, by optimizing the operation of the power plant based on predicted cloud movement information, the operating status of the panels can be adjusted according to the arrival or movement of clouds, allowing maximum utilization of solar radiation.

[0021] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0022] FIG. 1 is a block diagram illustrating the configuration of a solar power plant power generation prediction system according to one embodiment of the present invention.

[0023] Figure 2 is a flowchart of a method for predicting power generation from a solar power plant according to one embodiment of the present invention.

[0024] FIG. 3 is a diagram illustrating an example of collecting cloud images and recognizing objects through a sky camera in one embodiment of the present invention.

[0025] Figure 4 is a diagram showing a collection environment for collecting actual cloud images.

[0026] Figure 5 is a diagram illustrating collected cloud images and power generation data.

[0027] FIG. 6 is a diagram illustrating an example of a digital twin model for power generation prediction in one embodiment of the present invention.

[0028] FIGS. 7A to 7F illustrate examples of a digital twin environment in a solar power plant according to one embodiment of the present invention.

[0029] Figure 8 is a graph showing an example of the results of a power generation prediction simulation proposed in one embodiment of the present invention.

[0030] 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 below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided solely 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 present invention, and the present invention is defined solely by the scope of the claims.

[0031] The terminology used herein is for the purpose of describing embodiments only and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the mentioned components. Like reference numerals refer to like components throughout the specification, and "and / or" includes each and any combination of one or more of the mentioned components. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms. These terms are only used to distinguish one component from another. Therefore, it should be understood that a first component mentioned below may also be a second component within the technical spirit of the present invention.

[0032] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in their common sense to those skilled in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0033] Hereinafter, a solar power plant power generation prediction system (100) according to one embodiment of the present invention will be described with reference to FIG. 1.

[0034] FIG. 1 is a block diagram illustrating the configuration of a solar power plant power generation prediction system (100) according to one embodiment of the present invention.

[0035] A solar power plant power generation prediction system (100) according to one embodiment of the present invention includes a communication unit (110), a memory (120), and a processor (130).

[0036] The communication unit (110) collects location information and weather information of the solar power plant. The communication unit (110) may include both a wired communication module and a wireless communication module. The wired communication module may be implemented as a power line communication device, a telephone line communication device, a cable home (MoCA), Ethernet, IEEE1294, an integrated wired home network, and an RS-485 control device. In addition, the wireless communication module may be configured as a module for implementing functions such as WLAN (wireless LAN), Bluetooth, HDR WPAN, UWB, ZigBee, Impulse Radio, 60GHz WPAN, Binary-CDMA, wireless USB technology, wireless HDMI technology, and other 5G (5th generation communication), LTE-A (long term evolution-advanced), LTE (long term evolution), and Wi-Fi (wireless fidelity).

[0037] The memory (120) creates a digital twin model and stores programs for predicting the power generation of a solar power plant based on the digital twin model. Here, the memory (120) is a general term for non-volatile storage devices and volatile storage devices that maintain stored information even when power is not supplied. For example, the memory (120) may include NAND flash memory such as a compact flash (CF) card, an SD (secure digital) card, a memory stick, a solid-state drive (SSD), and a micro SD card, a magnetic computer storage device such as a hard disk drive (HDD), and an optical disc drive such as a CD-ROM or DVD-ROM.

[0038] The processor (130) can control at least one other component (e.g., hardware or software component) of the solar power plant power generation prediction system (100) by executing software such as a program, and can perform various data processing or calculations.

[0039] At this time, in one embodiment of the present invention, the processor (130) may use at least one of a machine learning, a neural network, or a deep learning algorithm as an artificial intelligence (AI) algorithm to generate an artificial intelligence algorithm. For example, at least one of a machine learning, a neural network, or a deep learning algorithm may be used as an artificial intelligence (AI) algorithm, and examples of the neural network may include models such as a CNN (Convolutional Neural Network), a DNN (Deep Neural Network), and an RNN (Recurrent Neural Network).

[0040] Hereinafter, a method performed by a solar power plant power generation system (100) according to one embodiment of the present invention will be described with reference to FIGS. 2 to 8.

[0041] Figure 2 is a flowchart of a method for predicting power generation from a solar power plant according to one embodiment of the present invention.

[0042] First, location information and weather information of the solar power plant are acquired (S110). Since the solar power plant is located in a fixed location, the location information may be preset. For weather information, one embodiment of the present invention captures a sky image corresponding to the solar power plant based on a sky camera installed in the solar power plant, recognizes cloud images included in the sky image as object information, and acquires weather information. At this time, the sky camera can be used together with a general camera to capture the state of the sky as a high-quality image. FIG. 3 is a diagram illustrating an example of collecting and object recognizing cloud images using a sky camera in one embodiment of the present invention. FIG. 4 is a diagram illustrating a collection environment for collecting actual cloud images.

[0043] In one example, image data acquired through a sky camera can be recognized as cloud objects using specific deep learning or computer vision techniques. Recognized cloud characteristics may include shape, direction of movement, and thickness. This information is obtained through analysis of images collected from the sky camera and is utilized in the creation of a digital twin model.

[0044] Additionally, one embodiment of the present invention can acquire and utilize various meteorological factors, such as atmospheric conditions, temperature, wind speed, and rainfall, as well as cloud images, as meteorological information. This information can be collected from local weather observation equipment or meteorological services.

[0045] Next, a digital twin model for simulating cloud movement is created based on the location of the solar power plant and the corresponding weather conditions (S120). At this time, the digital twin model can be further developed by incorporating real-time performance data from each solar panel within the power plant. This real-time performance data includes voltage, current, and power generation data obtained through monitoring systems installed within the power plant, allowing for an accurate representation of the status of each panel. Therefore, the generated digital twin model is created and provided by matching the performance data of each solar panel with the direction of cloud movement.

[0046] Figure 5 is a diagram illustrating collected cloud images and power generation data.

[0047] The generated digital twin model provides a virtual environment for cloud movement at locations corresponding to solar power plants. This provides a virtual world that accurately mimics the layout of the actual power plant, the placement of solar panels, and the position and movement of clouds. Furthermore, the digital twin model can be updated in real time to respond to changes in the real environment. For example, when new cloud images are collected from sky cameras or new performance data is received through sensors, this information can be reflected in the digital twin, updating the virtual world to ensure maximum consistency with the real world.

[0048] Next, local weather pattern information is input into the digital twin model to model cloud movement (S130). This process uses machine learning and meteorological algorithms to precisely predict cloud movement on the digital twin. It involves learning actual observed weather data and incorporating wind field information to simulate cloud position and velocity on the digital twin model. This allows the digital twin to accurately reflect the dynamic movement of clouds occurring in real-world environments in a virtual space.

[0049] Next, modeled cloud movement information is input into a pre-trained artificial intelligence model to obtain future time-based solar irradiance forecast information (S140), and solar panel thermal information corresponding to the predicted solar irradiance is calculated to predict the power generation of the solar power plant (S150). This process utilizes cloud movement information to precisely predict future solar irradiance, allowing predictions of the amount of sunlight each solar panel will receive. Furthermore, based on the predicted irradiance, the power that each solar panel within the power plant can be predicted. At this time, predictions of future power generation can be generated by considering various environmental factors such as panel efficiency, temperature, and shadows.

[0050] In this way, one embodiment of the present invention collects real-time data on the location of actual solar panels and meteorological conditions (such as cloud movement) to create a digital twin (such as a location-based meteorological environment simulation) and models cloud movement based on regional weather patterns. Based on the cloud movement information generated through the digital twin model, solar irradiance for a future time period can be predicted, and based on the irradiance and heat flux of the solar panels, the future power generation of a solar power plant can be accurately predicted. At this time, the predicted power generation can be for a very short period of time or for a long period of time.

[0051] Furthermore, one embodiment of the present invention can dynamically adjust the optimal layout of solar panels based on the predicted power generation of a solar power plant. That is, as described above, one embodiment of the present invention can accurately identify and predict the dynamic movement of clouds through digital twins, and utilize accumulated cloud movement information to calculate the optimal layout of solar panels.

[0052] At this time, the position of each panel can be dynamically adjusted, taking into account factors such as cloud movement patterns, size, and height. Here, the optimal arrangement refers to one that maximizes solar panel exposure while minimizing cloud obscuration, thereby increasing power generation efficiency. Once this optimal arrangement is determined, one embodiment of the present invention can provide the operator with an environment for generating maximum power, allowing the operator to make a final decision on the optimal arrangement based on cloud conditions and predicted solar irradiance.

[0053] Thus, according to one embodiment of the present invention, as cloud movement information continuously changes, the optimal placement of solar panels can be continuously optimized in response. This allows the power plant to always operate under optimal conditions, maximizing energy efficiency and ensuring stable power production.

[0054] Furthermore, one embodiment of the present invention continuously monitors real-world conditions through a digital twin model and continuously updates the predictive model to maintain more accurate power generation forecasts. Furthermore, as described above, the operation of a solar power plant can be optimized based on real-time, changing weather conditions.

[0055] Figure 6 is a diagram illustrating an example of a digital twin model for power generation prediction according to one embodiment of the present invention. This digital twin model can calculate power generation by reflecting the irradiance and weather information (temperature, etc.) input to the solar panel.

[0056] FIGS. 7A to 7F illustrate examples of a digital twin environment in a solar power plant according to one embodiment of the present invention.

[0057] First, Figure 7a illustrates the digital twin environment of a solar power plant. Figure 7b illustrates the simulation results for power generation calculations based on cloud images and movement directions in this environment. The blue area in the lower right corner represents the panel area obscured by clouds, while the yellow area on the left represents the area beginning to receive sunlight. Similarly, Figures 7c to 7f also illustrate the simulation results for power generation prediction based on digital twin-based cloud movement (direction and speed).

[0058] Figure 8 is a graph illustrating an example of the results of a power generation prediction simulation proposed in one embodiment of the present invention. The simulation was conducted on a clear day, and the accuracy of solar power generation prediction on cloudy days (overcast days) is significantly higher than that of existing models (e.g., AI-based power generation prediction data models).

[0059] Meanwhile, in the above description, steps S110 to S150 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Furthermore, some steps may be omitted as needed, and the order of steps may be changed. Furthermore, even if other details are omitted, the details described in FIG. 1 and FIGS. 2 to 8 are mutually applicable.

[0060] The embodiments of the present invention described above can be implemented as a program (or application) and stored in a medium to be executed in combination with a hardware server.

[0061] The above-described program may include codes coded in a computer language, such as C, C++, JAVA, or machine language, that can be read by the processor (CPU) of the computer through the device interface of the computer, so that the computer reads the program and executes the methods implemented as a program. Such codes may include functional codes related to functions that define functions necessary for executing the methods, and may include control codes related to execution procedures necessary for the processor of the computer to execute the functions according to a predetermined procedure. In addition, such codes may further include memory reference-related codes regarding which location (address address) of the internal or external memory of the computer should reference additional information or media necessary for the processor of the computer to execute the functions. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to send and receive during communication.

[0062] The above storage medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the program can be stored in various recording media on various servers that the computer can access or in various recording media on the user's computer. In addition, the medium can be distributed across network-connected computer systems, so that computer-readable code can be stored in a distributed manner.

[0063] The steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in a random access memory (RAM), a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, a CD-ROM, or any other form of computer-readable recording medium well known in the art to which the present invention pertains.

[0064] While the embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will appreciate that the present invention can be implemented in other specific forms without altering the technical concept or essential features thereof. Therefore, the embodiments described above should be understood to be illustrative in all respects and not restrictive.

[0065] It can be used in industrial fields to predict solar power plant power generation based on digital twin models.

Claims

1. In a method performed by a computer, Step of obtaining location information and weather information of solar power plants; A step of creating a digital twin model for simulating cloud movement based on regional information where the solar power plant is located and weather conditions corresponding to the regional information; A step of modeling cloud movement information by inputting local weather pattern information into the above digital twin model; A step of inputting the movement information of the modeled cloud into a pre-learned artificial intelligence model to obtain future time-based solar irradiance prediction information; and A step of predicting the power generation of a solar power plant by calculating the thermal information of a solar panel corresponding to the above solar irradiance prediction information, Method for predicting power generation of solar power plants through cloud movement prediction based on digital twin model.

2. In paragraph 1, The steps of obtaining location information and weather information of the above solar power plant are: A step of capturing a sky image corresponding to the solar power plant based on a sky camera installed in the solar power plant; and Including a step of recognizing a cloud image included in the above sky image as object information and acquiring it as the weather information. Method for predicting power generation of solar power plants through cloud movement prediction based on digital twin model.

3. In paragraph 2, The step of recognizing a cloud image included in the above sky image as object information and acquiring it as the above weather information is, Recognizing object information including the shape, movement direction and thickness of the cloud image and obtaining it as the weather information. Method for predicting power generation of solar power plants through cloud movement prediction based on digital twin model.

4. In paragraph 1, The step of creating a digital twin model for cloud movement simulation based on the regional information where the above solar power plant is located and the weather conditions corresponding to the regional information is as follows. The digital twin model is created by further reflecting real-time performance data from each solar panel. Method for predicting power generation of solar power plants through cloud movement prediction based on digital twin model.

5. In paragraph 1, Further comprising a step of dynamically adjusting the optimal arrangement of the solar panels based on the predicted power generation of the solar power plant. Method for predicting power generation of solar power plants through cloud movement prediction based on digital twin model.

6. Communication department that obtains location information and weather information of solar power plants; A memory that stores a program to create a digital twin model and predict the power generation of a solar power plant based on it. By executing the program stored in the above memory, a digital twin model for simulating cloud movement is generated based on the regional information where the solar power plant is located and the weather conditions corresponding to the regional information, and regional weather pattern information is input into the digital twin model to model cloud movement information, and the modeled cloud movement information is input into a pre-learned artificial intelligence model to obtain future time zone-specific solar irradiance prediction information, and then a processor is included to calculate the thermal information of the solar panel corresponding to the solar irradiance prediction information to predict the power generation of the solar power plant. A solar power plant power generation prediction system using digital twin-based cloud movement prediction.

7. In paragraph 6, The above processor further reflects real-time performance data of each solar panel to create the digital twin model. A solar power plant power generation prediction system using cloud movement prediction based on digital twin model.

8. In paragraph 6, The above processor dynamically adjusts the optimal arrangement of the solar panels based on the predicted power generation of the solar power plant. A solar power plant power generation prediction system using cloud movement prediction based on digital twin model.

Images