Data preprocessing method and device for detecting abnormalities in solar power plants

Abstract

The present disclosure relates to a data preprocessing method for detecting abnormalities in a solar power plant, performed by at least one processor, the data preprocessing method for detecting abnormalities in a solar power plant includes receiving inverter input / output data of the solar power plant, receiving a plurality of satellite images of solar radiation reaching the ground, preprocessing the inverter input / output data, and preprocessing the plurality of satellite images of solar radiation reaching the ground.

Description

[Technical Field]

[0001] The present disclosure relates to a data preprocessing method and apparatus for detecting abnormalities in a solar power plant, and more particularly to a method and apparatus for preprocessing inverter input / output data of a solar power plant and satellite images of solar radiation reaching the ground. [Background technology]

[0002] Recently, many countries have been investing heavily in the development of new and renewable energy sources in order to respond to climate change. In particular, solar power generation, which produces electricity from sunlight, is attracting attention as an alternative energy source of the future. As a result, the solar power generation-related industry is experiencing rapid growth.

[0003] Meanwhile, in solar power plants, various types of abnormal conditions or performance degradation can occur, such as a decrease in the power generation efficiency of solar panels due to dust, short circuits in inverter circuits, control abnormalities, etc. At this time, a considerable number of abnormal conditions lead to a decrease in power generation efficiency, but there is a problem in that it is difficult to immediately determine what type of abnormal condition has occurred based only on the fact or amount of change in the amount of power generation. Summary of the Invention [Problem to be solved by the invention]

[0004] To solve the above problems, the present disclosure provides a data preprocessing method for detecting abnormalities in a solar power plant, a computer-readable non-transitory recording medium having instructions recorded thereon, and a system (apparatus). [Means for solving the problem]

[0005] The present disclosure can be implemented in numerous ways, including as a method, a system (apparatus), or a non-transitory computer-readable storage medium having instructions recorded thereon.

[0006] A data preprocessing method for detecting abnormalities in a solar power plant, performed by at least one processor, includes receiving inverter input / output data of the solar power plant, receiving a plurality of satellite images of solar radiation reaching the ground, preprocessing the inverter input / output data, and preprocessing the plurality of satellite images of solar radiation reaching the ground.

[0007] In one embodiment of the present disclosure, the method further includes determining an abnormal state of the solar power plant based on the preprocessed inverter input / output data and the preprocessed satellite images of the solar radiation reaching the ground, wherein the abnormal state of the solar power plant includes at least one of an abnormal state of the inverter, an abnormal state of the solar panel connected to the inverter, or a decrease in performance of the solar panel.

[0008] In one embodiment of the present disclosure, the inverter input / output data includes hourly inverter input data and hourly inverter output data, and the step of preprocessing the inverter input / output data includes a step of estimating and filling in missing values in the inverter input / output data, and the missing values are estimated based on inverter input / output data for the same time period of other solar power plants in the same area as the solar power plant.

[0009] In one embodiment of the present disclosure, the inverter input / output data includes hourly inverter input data and hourly inverter output data, and the step of pre-processing the inverter input / output data includes the step of correcting the inverter input data and the inverter output data for the time periods after sunset and before sunrise to zero.

[0010] In one embodiment of the present disclosure, the inverter input / output data includes hourly inverter input data and hourly inverter output data, and the step of preprocessing the inverter input / output data includes a step of detecting outliers in the hourly inverter input data and the hourly inverter output data using an interquartile range (IQR) method, and a step of removing the detected outliers or estimating and writing the outliers.

[0011] In one embodiment of the present disclosure, the plurality of satellite images of solar radiation reaching the ground indicate the amount of solar radiation reaching the ground in the region, with RGB values of each pixel on the satellite map image for each hour, and the step of pre-processing the plurality of satellite images of solar radiation reaching the ground includes the step of extracting hourly solar radiation data for the region associated with the solar power plant based on the plurality of satellite images of solar radiation reaching the ground.

[0012] In one embodiment of the present disclosure, the step of preprocessing the plurality of satellite images of ground-reaching solar radiation includes the step of estimating and filling in RGB values of missing pixels in the plurality of satellite images of ground-reaching solar radiation, wherein the RGB values of the missing pixels are estimated using at least one of a kriging technique or an inverse distance weighting method.

[0013] In one embodiment of the present disclosure, the inverter input / output data includes hourly inverter input data and hourly inverter output data, and the method further includes a step of determining a time series similarity between the inverter input / output data and the hourly solar radiation data, and a step of synchronizing the time series of the inverter input / output data and the hourly solar radiation data based on the time series similarity.

[0014] A non-transitory computer-readable recording medium having recorded thereon instructions for executing the above-described method on a computer according to one embodiment of the present disclosure is provided.

[0015] An information processing system according to an embodiment of the present disclosure includes a communication module, a memory, and at least one processor coupled to the memory and configured to execute at least one computer-readable program stored in the memory, the at least one program including instructions for receiving inverter input / output data of a solar power plant, receiving a plurality of satellite images of ground-reaching solar radiation, pre-processing the inverter input / output data, and pre-processing the plurality of satellite images of ground-reaching solar radiation. [Effects of the Invention]

[0016] In various embodiments of the present disclosure, an abnormal condition of a solar power plant can be determined.

[0017] In various embodiments of the present disclosure, by determining the type of abnormal condition in a solar power plant, the abnormal condition can be resolved efficiently.

[0018] In various embodiments of the present disclosure, when a problem occurs at a solar power plant, it is possible to detect which abnormality in the equipment is causing the problem and take prompt and appropriate measures without the need for a manager to visit the site.

[0019] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by a person having ordinary skill in the art to which the present disclosure pertains (hereinafter referred to as "ordinary engineer") from the description in the claims. [Brief explanation of the drawings]

[0020] Non-limiting embodiments of the present disclosure will be described with reference to the accompanying drawings, as described below, in which like reference numerals indicate like elements, and in which: [Figure 1] FIG. 10 is a diagram illustrating an example of determining an abnormal state of a photovoltaic power plant according to an embodiment of the present disclosure. [Figure 2]1 is a schematic diagram illustrating a configuration in which an information processing system is communicatively connected to multiple user terminals to provide an anomaly detection service for a solar power plant according to an embodiment of the present disclosure. FIG. [Figure 3] 1 is a block diagram showing an internal configuration of a user terminal and an information processing system according to an embodiment of the present disclosure. [Figure 4] FIG. 1 is a block diagram illustrating a data pre-processing and anomaly detection method according to one embodiment of the present disclosure. [Figure 5] FIG. 2 is a block diagram illustrating an internal configuration and data input / output of a processor according to an embodiment of the present disclosure. [Figure 6] FIG. 1 illustrates multiple satellite images of ground-reaching solar radiation and hourly solar radiation data for a region associated with a solar power plant according to one embodiment of the present disclosure. [Figure 7] FIG. 10 illustrates an example of time-series data preprocessing according to an embodiment of the present disclosure. [Figure 8] FIG. 1 is an exemplary diagram illustrating an artificial neural network model according to one embodiment of the present disclosure. [Figure 9] 1 is a flowchart illustrating a data pre-processing method according to an embodiment of the present disclosure. [Figure 10] 1 is a flowchart illustrating a method for detecting an abnormality in solar power generation according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the accompanying drawings. However, in the following description, specific descriptions of well-known functions and configurations will be omitted if they may obscure the gist of the present disclosure.

[0022] In the accompanying drawings, identical or corresponding components are denoted by the same reference numerals. In addition, in the following description of the embodiments, duplicated descriptions of identical or corresponding components may be omitted. However, even if descriptions of components are omitted, it is not intended that such components are not included in the embodiments.

[0023] The advantages and features of the disclosed embodiments, as well as methods for achieving them, will become apparent from the following detailed description of the embodiments taken in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below, and may be embodied in various different forms. The present embodiments are provided solely so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0024] The terms used in this specification will be briefly explained, and the disclosed embodiments will be specifically described. The terms used in this specification are currently selected as widely used and general terms as much as possible, taking into consideration the functions in this disclosure. However, these terms may differ depending on the intentions of engineers in the relevant field, precedents, the emergence of new technologies, etc. In addition, in certain cases, the applicant may arbitrarily select terms, and in such cases, the meanings of these terms will be described in detail in the relevant description of the invention. Therefore, the terms used in this disclosure must be defined based on the meanings of the terms and the overall content of this disclosure, rather than simply by the names of the terms.

[0025] In this specification, the singular expression includes the plural expression unless the context clearly dictates otherwise. Furthermore, the plural expression includes the singular expression unless the context clearly dictates otherwise. When a part in the entire specification includes a certain element, this does not mean that it excludes other elements, but that it can further include other elements, unless otherwise specified.

[0026] Additionally, the terms "module" and "module" used in this specification refer to software or hardware components, and the "module" or "module" performs a certain function. However, the term "module" or "module" is not limited to software or hardware. A "module" or "module" may be configured to reside on an addressable storage medium or to execute one or more processors. Thus, by way of example, a "module" or "module" may include components such as software components, object-oriented software components, class components, and task components, as well as at least one of processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within a component and "module" or "module" may be combined into fewer components and "modules" or "modules," or further separated into additional components and "modules" or "modules."

[0027] According to one embodiment of the present disclosure, a "module" or "unit" may be implemented with a processor and memory. "Processor" should be broadly interpreted to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, etc. In some environments, "processor" may refer to an application specific integrated circuit (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), etc. "Processor" may also refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors in conjunction with a DSP core, or any other such configuration. Also, "memory" should be broadly interpreted to include any electronic component capable of storing electronic information. "Memory" may refer to various types of processor-readable media such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable-programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage devices, registers, etc. Memory is in electronic communication with a processor if the processor can read / write information from or write information to the memory. Memory that is integrated into a processor is in electronic communication with the processor.

[0028] In this disclosure, a remote terminal unit (RTU) may refer to a device that collects data from a remote location, converts the data into a transmittable format, and then transmits the data to a central base station. Specifically, the remote terminal unit may be configured to collect information from a main unit and perform a series of work procedures instructed by the main unit.

[0029] 1 is a diagram illustrating an example of determining an abnormal state of a solar power plant according to an embodiment of the present disclosure. In one embodiment, the abnormal state of the solar power plant can be determined based on a plurality of satellite images of solar radiation reaching the ground taken by a satellite 110 and / or input / output data of an inverter 124 connected to a solar panel 122 of a solar power plant 120.

[0030] The artificial satellite 110 may capture a satellite image of the amount of solar radiation reaching the ground. Specifically, the artificial satellite 110 may capture a satellite image of the amount of solar radiation reaching the ground at a predetermined time interval (e.g., every 10 minutes). Here, the satellite image of the amount of solar radiation reaching the ground may include information on the amount of solar radiation reaching the location where the solar power plant 120 is located. For example, the satellite image of the amount of solar radiation reaching the ground may display information on the amount of solar radiation reaching the location corresponding to each pixel according to the RGB value of each pixel included in the image.

[0031] In one embodiment, a plurality of satellite images of solar radiation reaching the ground captured by the artificial satellite 110 at different times may have RGB values of each pixel on the satellite map image at each time that indicate the amount of solar radiation reaching the ground in that area. For example, each pixel may be represented by a combination of red, green, and blue light source intensity values, each ranging from 0 to 255. In this case, the greater the amount of solar radiation reaching the ground in the area (e.g., specified by latitude and longitude) corresponding to each pixel, the closer to red it is displayed, and the smaller the amount of solar radiation, the closer to purple it is displayed, but this is not limited to this method.

[0032] The solar power plant 120 may include at least one solar panel 122 , at least one inverter 124 , and at least one remote terminal unit (RTU) 126 .

[0033] The solar panel 122 can generate DC power from sunlight. The inverter 124 is connected to the solar panel 122 and can convert the DC power generated by the solar panel 122 into AC power.

[0034] The remote terminal 126 is connected to the inverter 124 and can transmit input / output data of the inverter 124 to an information processing system or a user terminal. In this case, the inverter input / output data can include inverter input data per time (e.g., DC current data, DC voltage data, DC power data, etc. per time) and inverter output data per time (e.g., AC current data, AC voltage data, AC power data, AC frequency data, etc. per time).

[0035] 1 illustrates and describes one inverter connected to one solar panel, but this is not limiting. For example, one inverter may be connected to multiple solar panels to convert DC power generated by each of the multiple solar panels into AC power. Similarly, the present invention is not limited to connecting one remote terminal device to one inverter, and one remote terminal device may transmit input / output data of each of the multiple inverters to an information processing system or a user terminal.

[0036] The user terminal 130 may receive information associated with an abnormal state of the solar power plant 120. In one embodiment, the abnormal state of the solar power plant 120 may be determined based on inverter input / output data and multiple satellite images of solar radiation reaching the ground. In this case, the abnormal state of the solar power plant 120 may include, but is not limited to, at least one of an abnormal state of the inverter 124, an abnormal state of the solar panel 122 connected to the inverter 124, or a performance degradation of the solar panel 122.

[0037] 2 is a schematic diagram showing a configuration in which an information processing system 230 is communicatively coupled to multiple user terminals 210_1, 210_2, and 210_3 to provide a solar power plant anomaly detection service according to an embodiment of the present disclosure. In one embodiment, the information processing system 230 may include one or more server devices and / or databases, or one or more cloud computing service-based distributed computing devices and / or distributed databases, that can store, provide, and execute computer-executable programs (e.g., downloadable applications) and data related to the solar power plant anomaly detection service. For example, the information processing system 230 may include a separate system (e.g., a server) for the solar power plant anomaly detection service.

[0038] The solar power plant abnormality detection service provided by the information processing system 230 can be provided to users via applications installed in each of the plurality of user terminals 210_1, 210_2, and 210_3.

[0039] The plurality of user terminals 210_1, 210_2, and 210_3 can communicate with the information processing system 230 via the network 220. The network 220 may be configured to enable communication between the plurality of user terminals 210_1, 210_2, and 210_3 and the information processing system 230. Depending on the installation environment, the network 220 may be configured as a wired network such as Ethernet, power line communication, telephone line communication device, and RS-serial communication, a wireless network such as a mobile communication network, a wireless LAN (WLAN), Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. The communication method is not limited, and may include not only a communication method utilizing a communication network that the network 220 can include (for example, a mobile communication network, a wired Internet, a wireless Internet, a broadcast network, a satellite network, etc.), but also short-range wireless communication between the user terminals 210_1, 210_2, and 210_3.

[0040] 2 illustrates a mobile phone terminal 210_1, a tablet terminal 210_2, and a PC terminal 210_3 as examples of user terminals, but is not limited thereto. The user terminals 210_1, 210_2, and 210_3 may be any computing devices capable of wired and / or wireless communication and capable of installing and executing applications, etc. For example, the user terminals may include smartphones, mobile phones, navigation systems, computers, laptops, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), tablet PCs, game consoles, wearable devices, internet of things (IoT) devices, virtual reality (VR) devices, and augmented reality (AR) devices. Furthermore, while FIG. 2 illustrates three user terminals 210_1, 210_2, and 210_3 communicating with the information processing system 230 via the network 220, the present invention is not limited thereto. A different number of user terminals may be configured to communicate with the information processing system 230 via the network 220.

[0041] In one embodiment, the information processing system 230 can determine an abnormal state of the solar power plant and provide the determined abnormal state to the user terminals 210_1, 210_2, and 210_3. In Fig. 2, the information processing system 230 is described as determining an abnormal state of the solar power plant, but this is not limited thereto. For example, the user terminals 210_1, 210_2, and 210_3 can directly determine an abnormal state of the solar power plant.

[0042] FIG. 3 is a block diagram illustrating the internal configuration of a user terminal 210 and an information processing system 230 according to an embodiment of the present disclosure. The user terminal 210 may refer to any computing device capable of executing a solar power plant anomaly detection application or the like and capable of wired / wireless communication, and may include, for example, the mobile phone terminal 210_1, tablet terminal 210_2, or PC terminal 210_3 of FIG. 2 . As illustrated, the user terminal 210 may include a memory 312, a processor 314, a communication module 316, and an input / output interface 318. Similarly, the information processing system 230 may include a memory 332, a processor 334, a communication module 336, and an input / output interface 338. As illustrated in FIG. 3 , the user terminal 210 and the information processing system 230 may be configured to communicate information and / or data over the network 220 using their respective communication modules 316 and 336. Additionally, the input / output device 320 may be configured to input information and / or data to the user terminal 210 via the input / output interface 318 and to output information and / or data generated from the user terminal 210 .

[0043] The memories 312 and 332 may include any non-transitory computer-readable recording medium. According to one embodiment, the memories 312 and 332 may include a permanent mass storage device such as a read only memory (ROM), a disk drive, a solid state drive (SSD), a flash memory, or the like. As another example, a permanent mass storage device such as a ROM, an SSD, a flash memory, or a disk drive may be included in the user terminal 210 or the information processing system 230 as a separate permanent storage device distinct from the memory. The memories 312 and 332 may also store an operating system and at least one program code (e.g., code for an application associated with the solar power plant anomaly detection service).

[0044] Such software components may be loaded from a computer-readable recording medium separate from the memories 312, 332. Such separate computer-readable recording medium may include a recording medium directly connectable to the user terminal 210 and the information processing system 230, such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. As another example, the software components may be loaded into the memories 312, 332 via the communication modules 316, 336, which are not computer-readable recording media. For example, at least one program may be loaded into the memories 312, 332 based on a computer program (e.g., an application associated with an anomaly detection service for solar power plants) to be installed by a file provided via the network 220 by a developer or a file distribution system that distributes application installation files.

[0045] The processors 314, 334 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to the processors 314, 334 by the memories 312, 332 or the communications modules 316, 336. For example, the processors 314, 334 may be configured to execute received instructions according to program code stored in a storage device, such as the memories 312, 332.

[0046] The communication modules 316 and 336 may provide a configuration or function for the user terminal 210 and the information processing system 230 to communicate with each other via the network 220, and may provide a configuration or function for the user terminal 210 and / or the information processing system 230 to communicate with other user terminals or other systems (e.g., another cloud system). For example, a request or data (e.g., a request for detecting an abnormality in a solar power plant) generated by the processor 314 of the user terminal 210 in accordance with program code stored in a storage device such as the memory 312 may be transmitted to the information processing system 230 via the network 220 under the control of the communication module 316. Conversely, a control signal or command provided under the control of the processor 334 of the information processing system 230 may be received by the user terminal 210 via the communication module 316 of the user terminal 210 via the communication module 336 and the network 220. For example, the user terminal 210 may receive information on the presence or absence of an abnormality in the solar power plant and the abnormal state from the information processing system 230.

[0047] The input / output interface 318 may be a means for interfacing with the input / output device 320. For example, the input device may include a device such as a camera including an audio sensor and / or an image sensor, a keyboard, a microphone, or a mouse, and the output device may include a device such as a display, a speaker, or a haptic feedback device. As another example, the input / output interface 318 may be a means for interfacing with a device in which the configuration or functions for input and output are integrated into one, such as a touch screen. Although FIG. 3 illustrates the input / output device 320 as not being included in the user terminal 210, this is not limiting and the input / output device 320 may be configured as a single device together with the user terminal 210. Furthermore, the input / output interface 338 of the information processing system 230 may be a means for interfacing with an input or output device (not shown) that may be connected to or included in the information processing system 230. Although the input / output interfaces 318, 338 are shown in FIG. 3 as elements configured separately from the processors 314, 334, this is not limiting, and the input / output interfaces 318, 338 may be configured to be included in the processors 314, 334.

[0048] The user terminal 210 and the information processing system 230 may include more components than those shown in FIG. 3 . However, it is not necessary to explicitly show most of the conventional components. In one embodiment, the user terminal 210 may be implemented to include at least a portion of the input / output device 320 described above. The user terminal 210 may also include other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, a database, etc. For example, if the user terminal 210 is a smartphone, it may include components typically included in a smartphone. For example, the user terminal 210 may be implemented to further include various components such as an acceleration sensor, a gyro sensor, a microphone module, a camera module, various physical buttons, buttons using a touch panel, an input / output port, and a vibrator for vibration.

[0049] According to one embodiment, the processor 314 of the user terminal 210 may be configured to run an application or a web browser application that provides a solar power plant anomaly detection service. At this time, program code associated with the application may be loaded into the memory 312 of the user terminal 210. While the application is running, the processor 314 of the user terminal 210 may receive information and / or data provided from the input / output device 320 via the input / output interface 318 or from the information processing system 230 via the communication module 316, process the received information and / or data, and store it in the memory 312. Furthermore, such information and / or data may be provided to the information processing system 230 via the communication module 316.

[0050] While the application is running, the processor 314 can receive voice data, text, images, videos, etc. input or selected via an input device such as a touch screen, keyboard, camera including an audio sensor and / or image sensor, microphone, etc. coupled to the input / output interface 318, and can store the received voice data, text, images, videos, etc. in the memory 312 or provide them to the information processing system 230 via the communication module 316 and the network 220. In one embodiment, the processor 314 can receive user input input via the input device and provide data / requests corresponding to the received user input to the information processing system 230 via the network 220 and the communication module 316.

[0051] The processor 314 of the user terminal 210 can transmit and output information and / or data to the input / output device 320 via the input / output interface 318. For example, the processor 314 of the user terminal 210 can output the processed information and / or data via the input / output device 320, such as a display-capable device (e.g., a touch screen, a display, etc.), a sound-capable device (e.g., a speaker), etc. In one embodiment, the processor 314 can display an abnormal state of the solar power plant on the display of the user terminal 210.

[0052] The processor 334 of the information processing system 230 may be configured to manage, process, and / or store information and / or data received from the plurality of user terminals 210 and / or the plurality of external systems. The information and / or data processed by the processor 334 may be provided to the user terminal 210 via the communication module 336 and the network 220. In one embodiment, the processor 334 of the information processing system 230 may provide the abnormal status of the solar power plant to the user terminal 210 via the communication module 336 and the network 220 in response to a request for abnormality detection of the solar power plant received from the user terminal 210.

[0053] 4 is a block diagram illustrating a data preprocessing and anomaly detection method according to an embodiment of the present disclosure. An abnormal state of a solar power plant can be determined based on inverter input / output data 410 and multiple satellite images of solar radiation reaching the ground 420. In this case, the inverter input / output data 410 may be received from a remote terminal device of the solar power plant, and the satellite images of solar radiation reaching the ground 420 may be received from another server (e.g., a meteorological agency server).

[0054] Thereafter, data pre-processing 430 may be performed on each of the inverter input / output data 410 of the solar power plant and the satellite image of solar radiation reaching the ground 420. Specific examples of the data pre-processing 430 will be described in detail later with reference to FIGS. 5 and 9.

[0055] The pre-processed data may then be stored in database 440. A calculation 450 of predicted power generation of the solar power plant may be performed based on the pre-processed data and other data stored in database 440. A detection 460 of an abnormal state of the solar power plant may then be performed based on the calculated predicted power generation and various data stored in database 440. A specific example of detecting an abnormal state of the solar power plant will be described in detail below with reference to FIGS. 5 and 10.

[0056] 5 is a block diagram illustrating the internal configuration and data input / output of a processor 500 according to an embodiment of the present disclosure. The processor 500 may be a processor of an information processing system or a processor of a user terminal. As shown in the figure, the processor 500 may include a data preprocessing unit 510, a predicted power generation amount calculation unit 520, an abnormal state determination unit 530, and the like. The processor 500 may be configured with a single processor or multiple processors.

[0057] The data preprocessing unit 510 can preprocess inverter input / output data of the solar power plant. Specifically, the inverter input / output data can include hourly inverter input data (e.g., hourly DC current data, DC voltage data, DC power data, etc.) and hourly inverter output data (e.g., hourly AC current data, AC voltage data, AC power data, AC frequency data, etc.).

[0058] In one embodiment, the data preprocessing unit 510 can preprocess missing values (e.g., data values that are null or 0) in the inverter input / output data. Specifically, the data preprocessing unit 510 can estimate the values of the missing values in the inverter input / output data and write the estimated values in place of the missing values. This configuration makes it possible to compare, in a time series manner, the actual power generation amount of the photovoltaic power generation system with the predicted power generation amount of the photovoltaic power generation system estimated from hourly solar radiation data.

[0059] For example, if the inverter input / output data contains missing values, the data preprocessing unit 510 can estimate the missing values based on data within a predetermined range including the missing values (e.g., 10 minutes before and after the time corresponding to the missing values). For example, the data preprocessing unit 510 can estimate the missing values using linear interpolation under the assumption that the data within the predetermined range has a linear relationship with time. This may involve estimating the missing values using data from the same location but in a different time period.

[0060] Additionally or alternatively, the data preprocessing unit 510 can estimate missing values based on inverter input / output data for the same time period of other solar power plants located in the same area as the solar power plant or in neighboring areas. For example, the data preprocessing unit 510 can estimate missing values based on inverter input / output data for the same time period of other solar power plants located within a predetermined distance from the solar power plant (e.g., the average value of data for the same time period of other surrounding solar power plants), or estimate missing values by multiplying inverter input / output data for the same time period of other solar power plants by a correlation coefficient or correlation function calculated based on past inverter input / output data of the solar power plant. This may be estimation of missing values using data for the same time period or at other locations.

[0061] In one embodiment, the data pre-processing unit 510 may correct the inverter input data and inverter output data for the time periods after sunset and before sunrise when solar power generation is physically impossible to generate to 0. In this case, the reference sunset and sunrise times may be determined based on data provided by the Japan Meteorological Agency or satellite images.

[0062] In one embodiment, the data preprocessing unit 510 may preprocess a plurality of satellite images of solar radiation reaching the ground. For example, the data preprocessing unit 510 may estimate and write RGB values (e.g., null or 0) of missing pixels in the plurality of satellite images of solar radiation reaching the ground. For example, the data preprocessing unit 510 may estimate / estimate the RGB values of the missing pixels using a kriging method that linearly combines values surrounding the missing pixels, and may estimate the RGB values of the missing pixels using a so-called inverse distance weighting method that assigns a greater weight to the RGB values of pixels closer to the missing pixel during interpolation.

[0063] In one embodiment, the data preprocessing unit 510 may extract hourly solar radiation data for a region associated with the solar power plant based on a plurality of satellite images of solar radiation reaching the ground. The details of extracting the hourly solar radiation data will be described later with reference to FIG. 6.

[0064] In one embodiment, the data preprocessing unit 510 can detect abnormal values from the hourly inverter input data, hourly inverter output data, and hourly solar radiation data. After detecting the abnormal values, the data preprocessing unit 510 can remove the detected abnormal values or replace the abnormal values with estimated values obtained by the missing value estimation method described above.

[0065] For example, the data preprocessing unit 510 can detect outliers based on the mean and variance of data within a predetermined time period (e.g., 1 hour, 2 hours, etc.). For example, the data preprocessing unit 510 can determine whether specific data corresponds to an outlier based on a Z-score value that indicates how far a data value is from the mean using the standard deviation as a reference.

[0066] In another example, the data preprocessing unit 510 can detect outliers based on the median and mean absolute deviation of data within a predetermined time period (eg, 1 hour, 2 hours, etc.).

[0067] In yet another example, the data preprocessing unit 510 can detect outliers in the data based on the Interquartile Range (IQR) method. Specifically, the data preprocessing unit 510 can calculate the first quartile (Q1) and the third quartile (Q3) of the data within a predetermined time period, and then identify data outside the range of Q1-1.5 (Q3-Q1) to Q1+1.5 (Q3-Q1) as an outlier.

[0068] In one embodiment, the data pre-processing unit 510 can integrate the time axis between the inverter input / output data and the hourly solar radiation data by down / up sampling. Here, downsampling is a process of converting the frequency of the original time series into a time series with a lower frequency, and can be performed by summing, averaging, etc. Meanwhile, upsampling is a process of converting the frequency of the original time series into a time series with a higher frequency, and can be performed by applying a post-conversion interpolation methodology.

[0069] In one embodiment, the data preprocessing unit 510 may determine the time series similarity between the inverter input / output data and the hourly solar radiation data. Specifically, the data preprocessing unit 510 may measure the time series similarity between the inverter input / output data and the hourly solar radiation data using dynamic time warping (DTW). Dynamic time warping may be an algorithm that measures the similarity between two similar wavelengths. Additionally or alternatively, the data preprocessing unit 510 may measure the time series similarity between the inverter input / output data and the hourly solar radiation data using min-max scaling and a distance calculation method. In this case, the inverter input / output data and the hourly solar radiation data may be normalized using min-max scaling, and then the similarity between the two time series may be measured using a calculation method such as Euclidean distance or Mahalanobis distance.

[0070] Thereafter, the data preprocessing unit 510 can synchronize the time series of the inverter input / output data and the hourly solar radiation data based on the time series similarity, as will be described in detail later with reference to FIG.

[0071] The predicted energy production calculation unit 520 may estimate the predicted energy production of the solar power plant based on hourly solar radiation data for a region associated with the solar power plant. In one embodiment, the predicted energy production calculation unit 520 may estimate the predicted energy production using a machine learning model trained based on historical actual energy production and satellite images of historical solar radiation reaching the ground associated with the historical actual energy production. For example, the machine learning model may estimate the predicted energy production using XGboost, LGBM, CNN, or a reinforcement learning algorithm.

[0072] In another embodiment, the predicted power generation amount calculation unit 520 may estimate the predicted power generation amount using a time series prediction method (e.g., a fitting ARIMA model) or a time series confidence interval. In yet another embodiment, the predicted power generation amount calculation unit 520 may estimate the predicted power generation amount according to the performance of the solar panel using a physical power generation amount calculation formula.

[0073] The abnormal state determination unit 530 can determine an abnormal state of the solar power plant based on at least one of inverter input / output data of the solar power plant or hourly solar radiation data of an area associated with the solar power plant. Specifically, the abnormal state determination unit 530 can determine at least one of an abnormal state of the inverter, an abnormal state of the solar panels connected to the inverter, or a performance degradation of the solar panels.

[0074] In one embodiment, the abnormal state determination unit 530 can determine the actual power generation amount of the solar power plant based on the inverter input / output data, and then perform a primary verification to determine whether the difference between the predicted power generation amount calculated by the predicted power generation amount calculation unit 520 and the actual power generation amount exceeds a predetermined first threshold.

[0075] Thereafter, in response to determining that the difference between the expected power generation amount and the actual power generation amount exceeds a predetermined first threshold, the abnormal state determination unit 530 can perform a secondary verification to determine whether the difference between the historical average actual power generation amount of the solar power plant and the actual power generation amount exceeds a predetermined second threshold. For example, the abnormal state determination unit 530 can compare the actual power generation amount with an average value of the actual power generation amount from a predetermined period before to the present. In yet another example, the abnormal state determination unit 530 can compare the actual power generation amount with an average power generation amount of a past date corresponding to the current date (for example, if the current date is December 15th, the average power generation amount on December 15th in the past n years).

[0076] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the abnormal state determination unit 530 may calculate the power conversion efficiency of the inverter based on the inverter input / output data. Thereafter, the abnormal state determination unit 530 may determine that the inverter is in an abnormal state if the calculated power conversion efficiency of the inverter exceeds a predetermined normal operating power conversion efficiency range associated with the inverter of the solar power plant.

[0077] In one embodiment, the abnormal state determination unit 530 can determine an abnormal state of the inverter (e.g., inverter short circuit, electrical control failure, etc.) by comparing the calculated power conversion efficiency of the inverter with past power conversion efficiencies of the solar power plant inverter, even if the calculated power conversion efficiency of the inverter is within a predetermined normal operation power conversion efficiency range. For example, if the power conversion efficiency of the inverter suddenly decreases or increases at a rate equal to or greater than a predetermined threshold rate compared to the past power conversion efficiency, the abnormal state determination unit 530 can determine an abnormal state of the inverter.

[0078] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the abnormal state determination unit 530 can compare the expected power generation amount of the solar power plant with the hourly DC power input to the inverter to detect an abnormal state of the solar panel connected to the inverter (e.g., solar panel abnormality, shading within the panel, dust accumulation). For example, in response to determining that the hourly DC power input to the inverter is smaller than the expected power generation amount by a certain threshold or more, the abnormal state determination unit 530 can detect an abnormal state of the solar panel.

[0079] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the abnormal state determination unit 530 can compare the expected power generation amount of the solar power plant with the hourly AC power output from the inverter to detect an abnormal state of the inverter (e.g., a short circuit of the inverter, a failure in electrical control, etc.). For example, the abnormal state determination unit 530 can detect an abnormal state of the inverter in response to determining that the hourly AC power output from the inverter is smaller than the expected power generation amount by a certain threshold or more.

[0080] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the abnormal state determination unit 530 can detect a deterioration in the performance of the solar panels connected to the inverter (e.g., a decrease in the remaining lifespan of the solar panels, the need to replace the solar panels, etc.) if the hourly DC power value input to the inverter and the hourly AC power value output from the inverter both show a decreasing trend.

[0081] The internal configuration of the processor 500 shown in FIG. 5 is merely an example, and in some embodiments, other components may be included in addition to the internal configuration shown, or some components may be omitted. For example, if some of the internal components are omitted, the processor of the user terminal may be configured to perform the functions of the omitted internal components. Also, although the internal configuration of the processor 500 is described in FIG. 5 as being divided by function, this does not necessarily mean that the components are physically divided. Although the data preprocessing unit 510, the predicted power generation amount calculation unit 520, and the abnormal state determination unit 530 are described separately above, this is for the purpose of understanding the invention and is not limited to this.

[0082] With this configuration, when a problem occurs at a solar power plant, it is possible to determine which abnormality in the equipment is causing the problem and take prompt and appropriate measures without the need for a manager to be dispatched to the site.

[0083] FIG. 6 illustrates multiple satellite images 610 of solar radiation reaching the ground and hourly solar radiation data 620 for an area associated with a solar power plant according to an embodiment of the present disclosure. The satellite image 612 of solar radiation reaching the ground may include multiple satellite images captured at predetermined intervals (e.g., 10 minutes). As illustrated, one satellite image 612 of solar radiation reaching the ground may display the solar radiation reaching the ground for each area using pixel colors (or RGB values). Pixels displayed in white in the satellite image 612 of solar radiation reaching the ground in FIG. 6 may be missing values. The RGB values of the missing pixels may be estimated and filled in using the above-described embodiment of FIG. 5.

[0084] The RGB values of each pixel in the satellite image of solar radiation reaching the ground 612 can indicate the amount of solar radiation reaching the ground in that area. For example, a pixel with a longer color wavelength (i.e., closer to red) can indicate a higher amount of solar radiation reaching the ground in that area, and a pixel with a shorter color wavelength (i.e., closer to purple) can indicate a lower amount of solar radiation reaching the ground in that area (see color chart 614).

[0085] In one embodiment, hourly solar radiation data 620 for a region associated with a solar power plant can be extracted from multiple satellite images of solar radiation reaching ground 610. For example, the amount of solar radiation reaching ground at a particular time can be extracted by comparing the RGB values of pixels corresponding to the longitude and latitude values of the region associated with the solar power plant in the satellite images of solar radiation reaching ground 610 with the RGB values in color table 614. This process can be repeated for multiple satellite images of solar radiation reaching ground to extract / generate hourly solar radiation data 620 for the region associated with the solar power plant.

[0086] In one embodiment, the processor may estimate the expected hourly power generation of the solar power plant based on the hourly solar radiation data 620.

[0087] 7 illustrates an example of time-series data preprocessing according to an embodiment of the present disclosure. In one embodiment, the processor determines a time-series similarity between the inverter input / output data and the hourly solar radiation data, and then synchronizes the time series of the inverter input / output data and the hourly solar radiation data based on the time-series similarity.

[0088] For example, a first graph 712 displaying one of the inverter input / output data and the hourly solar radiation data can be converted to have the same time interval as the other of the inverter input / output data and the hourly solar radiation data by up-sampling it to a second graph 714. Conversely, when one of the inverter input / output data and the hourly solar radiation data is displayed on the second graph 714, the second graph 714 can be down-sampled to the first graph 712 to be converted to have the same time interval as the other of the inverter input / output data and the hourly solar radiation data.

[0089] On the other hand, assuming that the third graph 722 and the fifth graph 732 are graphs displaying inverter input / output data and solar radiation data, respectively, it may be difficult to compare the inverter input / output data and solar radiation data in time series. This is because there is a time difference between the inverter input / output data and solar radiation data in the third graph 722, and the time lengths of the inverter input / output data and solar radiation data in the fifth graph 732 are different.

[0090] To solve this problem, in one embodiment, the time series of inverter input / output data and solar radiation data can be synchronized using dynamic time warping (DTW) or the like. The inverter input / output data and solar radiation data in the third graph 722 and the fifth graph 732, respectively, can be matched with each other by determining the time series similarity using dynamic time warping or the like, as in the fourth graph 724 and the sixth graph 734. The processor synchronizes the time series of the inverter input / output data and the solar radiation data based on the determined time series similarity, thereby enabling the inverter input / output data and the solar radiation data to be compared in time series.

[0091] 8 is an exemplary diagram illustrating an artificial neural network model 800 according to an embodiment of the present disclosure. The artificial neural network model 800 is an example of a machine learning model, which is a statistical learning algorithm or a structure for executing the algorithm that is implemented based on the structure of a biological neural network in machine learning technology and cognitive science.

[0092] According to one embodiment, the artificial neural network model 800 may represent a machine learning model with problem-solving capabilities, in which nodes, which are artificial neurons formed by synaptic connections like biological neural networks, repeatedly adjust synaptic weights to learn to reduce the error between a correct output corresponding to a specific input and an inferred output. For example, the artificial neural network model 800 may include any probability model, neural network model, etc. used in artificial intelligence learning methods such as machine learning and deep learning.

[0093] According to one embodiment, the above-described model for estimating the expected power generation of a solar power plant may be generated in the form of an artificial neural network model 800. For example, the artificial neural network model 800 may receive hourly solar radiation data for a region associated with the solar power plant and estimate the expected power generation based thereon.

[0094] The artificial neural network model 800 is implemented as a multilayer perceptron (MLP) composed of multiple nodes and connections between them. The artificial neural network model 800 according to this embodiment can be implemented using one of various artificial neural network model structures, including an MLP. As shown in FIG. 8, the artificial neural network model 800 includes an input layer 820 that receives an input signal or data 810 from the outside, an output layer 840 that outputs an output signal or data 850 corresponding to the input data, and n (where n is a positive integer) hidden layers 830_1 to 830_n positioned between the input layer 820 and the output layer 840. The hidden layers 830_1 to 830_n receive signals from the hidden layers 830_1 to 830_n and output the signals to the outside.

[0095] The artificial neural network model 800 can be trained using a supervised learning method, in which the model learns to optimize its ability to solve problems using a teacher signal (correct answer), or an unsupervised learning method, in which no teacher signal is required. According to one embodiment, the information processing system can train the artificial neural network model 800 using satellite images of past actual power generation and past solar radiation reaching the ground associated with the past actual power generation.

[0096] According to one embodiment, the information processing system can directly generate training data for training the artificial neural network model 800. For example, the information processing system can generate a training data set including historical actual power generation and satellite images of historical solar radiation reaching the ground correlated with the historical actual power generation. The information processing system can then train the artificial neural network model 800 to calculate projected power generation based on the generated training data set.

[0097] According to one embodiment, the input variables of the artificial neural network model 800 may include hourly solar radiation data. When the input variables are input via the input layer 820, the output variable output from the output layer 840 of the artificial neural network model 800 may be the expected power generation of the solar power plant.

[0098] In this way, the input layer 820 and output layer 840 of the artificial neural network model 800 are matched with a plurality of output variables corresponding to a plurality of input variables, and the synaptic values between the nodes included in the input layer 820, hidden layers 830_1-830_n, and output layer 840 are adjusted, thereby enabling learning to extract a correct output corresponding to a specific input. This learning process makes it possible to grasp the characteristics hidden in the input variables of the artificial neural network model 800, and adjust the synaptic values (or weights) between the nodes of the artificial neural network model 800 so as to reduce the error between the output variables calculated based on the input variables and the target output. In addition, the information processing system can learn an algorithm that receives hourly solar radiation data as input, and learn in a way that minimizes loss from the predicted power generation (i.e., annotation information).

[0099] Using the artificial neural network model 800 trained in this way, the expected power generation amount of the solar power plant can be estimated.

[0100] 9 is a flowchart illustrating a data preprocessing method 900 according to an embodiment of the present disclosure. The data preprocessing method 900 may begin by at least one processor receiving inverter input / output data of a solar power plant (S910). At this time, the inverter input / output data may include inverter input data per time (e.g., DC current data, DC voltage data, etc. per time) and inverter output data per time (e.g., AC current data, AC voltage data, AC frequency, etc. per time).

[0101] The processor can then receive a plurality of satellite images of solar radiation reaching the ground (S920), where the RGB values of each pixel on the satellite map image for each hour of the plurality of satellite images of solar radiation reaching the ground in the area can indicate the amount of solar radiation reaching the ground in the area.

[0102] The processor may then preprocess the inverter input / output data (S930). In one embodiment, the processor may preprocess the inverter input / output data by estimating and filling in missing values in the inverter input / output data. Specifically, the processor may estimate the missing values based on inverter input / output data for the same time period of other solar power plants in the same region as the solar power plant.

[0103] In another embodiment, the processor can preprocess the inverter input / output data by modifying the inverter input and output data to zero during the post-sunset and pre-sunrise periods.

[0104] In yet another embodiment, the processor may preprocess the inverter input / output data by detecting outliers in the hourly inverter input data and hourly inverter output data using an interquartile range (IQR) method, and removing the detected outliers or estimating and inserting the outliers.

[0105] The processor may then preprocess the plurality of satellite images of ground-reaching solar radiation (S940). In one embodiment, the processor may preprocess the plurality of satellite images of ground-reaching solar radiation by estimating and filling in RGB values of missing pixels in the plurality of satellite images of ground-reaching solar radiation. Specifically, the processor may estimate RGB values of the missing pixels using at least one of a kriging technique or an inverse distance weighting method.

[0106] In another embodiment, the processor may preprocess the plurality of satellite images of solar radiation reaching the ground by extracting hourly solar radiation data for a region associated with the solar power plant based on the plurality of satellite images of solar radiation reaching the ground, where the plurality of satellite images of solar radiation reaching the ground may have RGB values of each pixel on the hourly satellite map image that indicate the amount of solar radiation reaching the ground in the region.

[0107] Additionally, the processor may determine a time series similarity between the inverter input / output data and the hourly solar radiation data, and synchronize the time series of the inverter input / output data and the hourly solar radiation data based on the time series similarity.

[0108] Thereafter, the processor can determine an abnormal state of the solar power plant based on the preprocessed inverter input / output data and the preprocessed satellite images of the solar radiation reaching the ground, where the abnormal state of the solar power plant can include at least one of an abnormal state of the inverter, an abnormal state of the solar panel connected to the inverter, or a performance degradation of the solar panel.

[0109] 10 is a flowchart illustrating a method 1000 for detecting an abnormality in solar power generation according to an embodiment of the present disclosure. The method 1000 for detecting an abnormality in solar power generation can be started by at least one processor receiving input / output data of an inverter in a solar power plant (S1010).

[0110] Thereafter, the at least one processor may receive hourly solar radiation data for an area associated with the solar power plant (S1020). In one embodiment, the at least one processor may receive a plurality of satellite images of solar radiation reaching the ground and extract hourly solar radiation data for an area associated with the solar power plant based on the plurality of satellite images of solar radiation reaching the ground. In this case, the plurality of satellite images of solar radiation reaching the ground may have RGB values of each pixel on the hourly satellite map image that indicate the amount of solar radiation reaching the ground in the area.

[0111] Thereafter, the at least one processor may determine an abnormal state of the solar power plant based on at least one of the inverter input / output data or the hourly solar radiation data (S1030). At this time, the abnormal state of the solar power plant may include at least one of an abnormal state of the inverter, an abnormal state of the solar panel connected to the inverter, or a performance degradation of the solar panel.

[0112] In one embodiment, the at least one processor may estimate expected power generation of the solar power plant based on hourly solar radiation data, determine actual power generation of the solar power plant based on inverter input / output data, and perform a first verification to determine whether a difference between the expected power generation and the actual power generation exceeds a predetermined first threshold, where the expected power generation is estimated using a machine learning model, and the machine learning model may be trained based on historical actual power generation and satellite images of historical solar radiation reaching the ground associated with the historical actual power generation.

[0113] In one embodiment, in response to determining that the difference between the expected power generation and the actual power generation exceeds a first predetermined threshold, the at least one processor may perform a secondary verification to determine whether the difference between the historical average actual power generation of the solar power plant and the actual power generation exceeds a second predetermined threshold.

[0114] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the at least one processor may calculate a power conversion efficiency of the inverter based on the inverter input / output data, and determine that the inverter is in an abnormal state if the calculated power conversion efficiency of the inverter exceeds a predetermined normal operating power conversion efficiency range associated with the inverter of the solar power plant. In another embodiment, the at least one processor may compare the calculated power conversion efficiency of the inverter with a historical power conversion efficiency of the solar power plant inverter if the calculated power conversion efficiency of the inverter is within the predetermined normal operating power conversion efficiency range, and determine that the inverter is in an abnormal state.

[0115] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the at least one processor can detect an abnormal state of the solar panels connected to the inverter by comparing the expected power generation amount of the solar power plant with the hourly DC power input to the inverter.

[0116] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the at least one processor can detect an abnormal state of the inverter by comparing the expected power generation amount of the solar power plant with the hourly AC power output from the inverter.

[0117] In one embodiment, in response to determining that the solar power plant is in an abnormal state, the at least one processor can detect a decrease in performance of the solar panels connected to the inverter if both the hourly DC power value input to the inverter and the hourly AC power value output from the inverter show a decreasing trend.

[0118] 9 and 10 and the above description are merely examples, and may be implemented differently in some embodiments. For example, in some embodiments, the order of the steps may be changed, some steps may be repeated, some steps may be omitted, or some steps may be added.

[0119] The above-described method may be provided as a computer program stored on a computer-readable recording medium for execution by a computer. The medium may continuously store a computer-executable program or temporarily store it for execution or download. The medium may also be various recording or storage means in the form of a single piece of hardware or multiple pieces of hardware combined together. The medium is not limited to media directly connected to a computer system but may also be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and ROM, RAM, flash memory, etc., configured to store program instructions. Other examples of media include recording or storage media managed by app stores that distribute applications and other sites or servers that provide or distribute various software.

[0120] The methods, operations, or techniques of the present disclosure may be implemented by various means. For example, such techniques may be implemented in hardware, firmware, software, or a combination thereof. Those of ordinary skill in the art will understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the present disclosure may be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design requirements imposed on the overall system. Those of ordinary skill in the art may implement the described functionality in various ways for each particular application, but such implementations should not be interpreted as departing from the scope of the present disclosure.

[0121] In a hardware implementation, the processing units used to perform the techniques may be implemented within one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described in this disclosure, computers, or combinations thereof.

[0122] Thus, the various illustrative logic blocks, modules, and circuits described in connection with this disclosure may be implemented with or performed by a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other configuration.

[0123] In a firmware and / or software implementation, the techniques may be implemented with instructions stored on a computer-readable medium such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage device, etc. The instructions may be executable by one or more processors and may cause the processors to perform certain aspects of the functions described in this disclosure.

[0124] While the embodiments described above have been described as utilizing aspects of the presently disclosed subject matter on one or more stand-alone computer systems, the present disclosure is not limited thereto and may be implemented in conjunction with any computing environment, such as a network or distributed computing environment. Furthermore, in this disclosure, aspects of the subject matter may be implemented on multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include PCs, network servers, and handheld devices.

[0125] Although the present disclosure has been described herein with respect to some embodiments, various modifications and variations that are apparent to those skilled in the art to which the present disclosure pertains can be made without departing from the scope of the present disclosure, and such modifications and variations should be considered to fall within the scope of the claims appended hereto.

Claims

1. 1. A data pre-processing method for detecting anomalies in a solar power plant, performed by at least one processor, comprising: receiving inverter input / output data of a solar power plant; receiving a plurality of satellite images of ground-reaching solar radiation; preprocessing the inverter input / output data; preprocessing the plurality of satellite images of ground-reaching solar radiation; A data preprocessing method, including:

2. determining an abnormal state of the solar power plant based on the preprocessed inverter input / output data and the plurality of preprocessed satellite images of ground-reaching solar radiation; further comprising The data preprocessing method according to claim 1 , wherein the abnormal state of the solar power plant includes at least one of an abnormal state of the inverter, an abnormal state of a solar panel connected to the inverter, or a deterioration in performance of a solar panel.

3. the inverter input / output data includes inverter input data for each time period and inverter output data for each time period; The step of preprocessing the inverter input / output data includes: a step of estimating and filling in missing values in the inverter input / output data; The missing values are The data preprocessing method according to claim 1 , wherein the estimation is based on inverter input / output data for the same time period of other solar power plants in the same area as the solar power plant.

4. the inverter input / output data includes inverter input data for each time period and inverter output data for each time period; The step of preprocessing the inverter input / output data includes: Step of correcting the inverter input data and inverter output data to 0 during the time periods after sunset and before sunrise. The data preprocessing method of claim 1 , comprising:

5. the inverter input / output data includes inverter input data for each time period and inverter output data for each time period; The step of preprocessing the inverter input / output data includes: Detecting outliers in the hourly inverter input data and the hourly inverter output data using an interquartile range (IQR) technique; removing the detected abnormal value or estimating and writing the abnormal value; The data preprocessing method of claim 1 , comprising:

6. The plurality of satellite images of solar radiation reaching the ground indicate the amount of solar radiation reaching the ground in the area in question, with RGB values of each pixel on the satellite map image for each hour; The step of pre-processing the plurality of satellite images of ground-reaching solar radiation includes: extracting hourly solar radiation data for a region associated with the solar power plant based on the plurality of satellite images of ground-reaching solar radiation; The data preprocessing method of claim 1 , comprising:

7. The step of pre-processing the plurality of satellite images of ground-reaching solar radiation includes: estimating and filling in RGB values of missing pixels in the plurality of satellite images of ground-reaching solar radiation; The data preprocessing method of claim 6 , wherein the RGB values of the missing pixels are estimated using at least one of a kriging technique or an inverse distance weighting method.

8. the inverter input / output data includes hourly inverter input data and hourly inverter output data, and determining a time series similarity between the inverter input / output data and the hourly solar radiation amount data; a step of synchronizing the time series of the inverter input / output data and the time series of the hourly solar radiation amount data based on the time series similarity; The data preprocessing method of claim 6 , further comprising:

9. A non-transitory computer-readable recording medium having recorded thereon instructions for executing the method of claim 1 on a computer.

10. An information processing system, a communication module; Memory and at least one processor coupled to the memory and configured to execute at least one computer-readable program contained in the memory; Including, The at least one program Receive input / output data from the inverter of the solar power plant; Receive multiple satellite images of solar radiation reaching the ground, preprocessing the inverter input / output data; An information processing system including instructions for preprocessing the plurality of satellite images of ground-reaching solar radiation.

Images