KR102642564B1 - Method and system for diagnosing abnormalities in renewable energy generators - Google Patents

Abstract

The present disclosure relates to a method for diagnosing abnormalities in a renewable energy generator based on pseudo-day search, which is performed by at least one processor. The renewable energy generator abnormality diagnosis method includes the steps of acquiring electrical signal data of the renewable energy generator, acquiring weather observation data, acquiring power generation data of the renewable energy generator, and electrical signal data, weather observation data, and power generation data. Based on this, it includes diagnosing abnormalities in the renewable energy generator.

Description

Renewable energy generator abnormality diagnosis method and system {METHOD AND SYSTEM FOR DIAGNOSING ABNORMALITIES IN RENEWABLE ENERGY GENERATORS}

The present disclosure relates to a method and system for diagnosing abnormalities in renewable energy generators, and specifically relates to a method and system for diagnosing abnormalities in renewable energy generators based on electrical signal data, weather observation data, and power generation data.

Recently, many countries are investing heavily in renewable energy development to combat climate change. Among renewable energy development projects, generating electricity from wind and solar energy is receiving attention as a future alternative energy source.

In order to improve the operation rate of these renewable energy generators and reduce maintenance costs, it is very important to quickly detect any abnormalities in the generator and take action. Here, since meteorological phenomena can have a dominant effect on renewable energy generators, abnormality diagnosis methods using only electrical signals, excluding meteorological phenomena, often produce inaccurate diagnosis results. Additionally, there is a problem of increasing unnecessary maintenance costs due to inaccurate diagnosis.

The present disclosure provides a method for diagnosing abnormalities in a renewable energy generator, a computer program stored in a recording medium, and a system (device) to solve the above problems.

The present disclosure may be implemented in various ways, including as a method, system (device), or computer program stored in a readable storage medium.

In one embodiment of the present disclosure, a method for diagnosing abnormalities in a renewable energy generator based on pseudo-day search, performed by at least one processor, comprising: acquiring electrical signal data of the renewable energy generator; acquiring weather observation data; , Obtaining power generation data of the renewable energy generator and diagnosing abnormalities in the renewable energy generator based on electrical signal data, weather observation data, and power generation data.

In one embodiment of the present disclosure, the weather observation data includes at least one of data collected by a weather sensor placed near a renewable energy generator or data acquired by a weather satellite.

In one embodiment of the present disclosure, the electrical signal data includes past electrical signal data and current electrical signal data, the weather observation data includes past weather observation data and current weather observation data, and the power generation data includes past power generation data and The step of diagnosing an abnormality of the renewable energy generator, including current power generation data, determines at least one similarity date by calculating the similarity between past electrical signal data and past observation data, and current electrical signal data and current weather observation data. A step of deriving a power generation data probability distribution based on data associated with at least one similar day among past power generation data, and diagnosing an abnormality in a renewable energy generator based on the power generation data probability distribution and current power generation data. How to diagnose problems with renewable energy generators.

In one embodiment of the present disclosure, the electrical signal data includes current sub-electrical signal data and a plurality of past sub-electrical signal data, and the meteorological observation data includes current sub-meteorological observation data and a plurality of past sub-meteorological observation data. , The step of diagnosing an abnormality in the renewable energy generator includes calculating a first set of similarities between the current sub-electrical signal data and each of the plurality of past sub-electrical signal data, the current sub-meteorological observation data and the plurality of past sub-meteorological observations. Calculating a second set of similarities between each of the data and determining at least one similarity date based on the first set of similarities and the second set of similarities.

In one embodiment of the present disclosure, determining at least one similarity date includes calculating a third set of similarities by applying weights to each of the first set of similarities and the second set of similarities, and a third set of similarities. and determining at least one similar date based on the similarity of the set.

In one embodiment of the present disclosure, the power generation data includes current sub-generation data and a plurality of past sub-generation data, and the step of diagnosing an abnormality in the renewable energy generator includes at least one similar date among the plurality of past sub-generation data. It further includes extracting at least one associated past sub-generation data and diagnosing an abnormality in the renewable energy generator based on the at least one past sub-generation data and the current sub-generation data.

In one embodiment of the present disclosure, the weight includes being determined using XAI (eXplanable AI).

In one embodiment of the present disclosure, the step of diagnosing an abnormality in a renewable energy generator includes processing at least one past sub-generation data to follow a normal distribution. Based on the processed past power generation data and current sub-generation data, It further includes performing inference and diagnosing an abnormality in the renewable energy generator based on the statistical inference results.

In order to execute the method according to an embodiment of the present disclosure on a computer, a computer program stored in a computer-readable recording medium may be provided.

In one embodiment of the present disclosure, an information processing system includes a communication module, a memory, and at least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory, and at least one The program acquires electrical signal data of the renewable energy generator, acquires weather observation data, acquires power generation data of the renewable energy generator, and determines the abnormality of the renewable energy generator based on the electrical signal data, weather observation data, and power generation data. May include commands for diagnosing.

In various embodiments of the present disclosure, an abnormal state of a renewable energy generator may be diagnosed.

In various embodiments of the present disclosure, in order to diagnose an abnormal state of a renewable energy generator, more accurate abnormal state diagnosis can be made by considering weather observation data closely related to the generator state.

In various embodiments of the present disclosure, the operation rate of a renewable energy generator can be improved by more accurately diagnosing abnormal conditions.

In various embodiments of the present disclosure, when a problem occurs in a renewable energy generator, maintenance costs for the generator can be reduced by detecting abnormalities in the generator with high accuracy and taking quick and appropriate measures.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be explained by those skilled in the art in the technical field to which this disclosure pertains from the description of the claims (hereinafter referred to as 'the person skilled in the art'). can be clearly understood.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, in which like reference numerals indicate like elements, but are not limited thereto.
1 is a diagram illustrating an example of a method for diagnosing abnormalities in a renewable energy generator according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a configuration in which an information processing system is connected to communicate with a plurality of user terminals in order to diagnose abnormalities in a renewable energy generator according to an embodiment of the present disclosure.
Figure 3 is a block diagram showing the internal configuration of a user terminal and an information processing system according to an embodiment of the present disclosure.
Figure 4 is a block diagram showing a similar date search and similar date determination method according to an embodiment of the present disclosure.
Figure 5 is a block diagram showing the internal configuration of a processor according to an embodiment of the present disclosure.
Figure 6 is a block diagram showing an example of processing data acquired by a meteorological satellite according to an embodiment of the present disclosure.
FIG. 7 is a diagram illustrating an example of processing data acquired by a meteorological satellite according to an embodiment of the present disclosure.
FIG. 8 is a diagram illustrating an example of diagnosing an abnormality in a generator through statistical inference according to an embodiment of the present disclosure.
Figure 9 is a diagram illustrating an example of determining a similar date by considering a weight of similarity according to an embodiment of the present disclosure.
Figure 10 is an exemplary diagram showing an artificial neural network model according to an embodiment of the present disclosure.
Figure 11 is a flowchart showing a method for diagnosing abnormalities in a renewable energy generator according to an embodiment of the present disclosure.

Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, detailed descriptions of well-known functions or configurations will be omitted if there is a risk of unnecessarily obscuring the gist of the present disclosure.

In the accompanying drawings, identical or corresponding components are given the same reference numerals. Additionally, in the description of the following embodiments, overlapping 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 any embodiment.

Advantages and features of the disclosed embodiments and methods for achieving them will become clear by referring to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the present disclosure is complete and that the present disclosure does not convey the scope of the invention to those skilled in the art. It is provided only for complete information.

Terms used in this specification will be briefly described, and the disclosed embodiments will be described in detail. The terms used in this specification are general terms that are currently widely used as much as possible while considering the function in the present disclosure, but this may vary depending on the intention or precedent of a technician working in the related field, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant invention. Accordingly, the terms used in this disclosure should be defined based on the meaning of the term and the overall content of the present disclosure, rather than simply the name of the term.

In this specification, singular expressions include plural expressions, unless the context clearly specifies the singular. Additionally, plural expressions include singular expressions, unless the context clearly specifies plural expressions. When it is said that a certain part includes a certain element throughout the specification, this does not mean excluding other elements, but may further include other elements, unless specifically stated to the contrary.

Additionally, the term 'module' or 'unit' used in the specification refers to a software or hardware component, and the 'module' or 'unit' performs certain roles. However, 'module' or 'unit' is not limited to software or hardware. A 'module' or 'unit' may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a 'module' or 'part' refers to components such as software components, object-oriented software components, class components and task components, processes, functions and properties. , procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and 'modules' or 'parts' may be combined into smaller components and 'modules' or 'parts' or further components and 'modules' or 'parts'. Could be further separated.

According to an embodiment of the present disclosure, a 'module' or 'unit' may be implemented with a processor and memory. 'Processor' should be interpreted broadly to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some contexts, 'processor' may refer to an application-specific integrated circuit (ASIC), programmable logic device (PLD), field programmable gate array (FPGA), etc. 'Processor' refers to a combination of processing devices, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such combination of configurations. You may. Additionally, 'memory' should be interpreted broadly to include any electronic component capable of storing electronic information. 'Memory' refers to 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), May also refer to various types of processor-readable media, such as electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, etc. A memory is said to be in electronic communication with a processor if the processor can read information from and/or write information to the memory. The memory integrated into the processor is in electronic communication with the processor.

In the present disclosure, 'system' may include at least one of a server device and a cloud device, but is not limited thereto. For example, a system may consist of one or more server devices. As another example, a system may consist of one or more cloud devices. As another example, the system may be operated with a server device and a cloud device configured together.

In the present disclosure, 'renewable energy' may refer to energy used by converting renewable energy including sunlight, water, geothermal heat, precipitation, biological organisms, etc. Additionally, ‘renewable energy generators’ may include, but are not limited to, solar power generators and wind power generators.

In the present disclosure, 'similar date' may refer to a date having past power generation data (or data associated with power generation) with a similar value to current power generation data (or data associated with power generation). A similar day may be determined by a similar day search algorithm, and at least one similar date may be determined. In other words, statistical inference can be performed based on the power generation amount of a plurality of similar days and the current power generation amount, and through this, it is possible to diagnose whether the generator is abnormal. Here, data related to power generation may include electrical signal data, weather observation data, etc.

1 is a diagram illustrating an example of a method for diagnosing abnormalities in a renewable energy generator according to an embodiment of the present disclosure. In one embodiment, diagnosis of an abnormality in a renewable energy generator may be determined based on current power generation data 110 and past power generation data 120 of the renewable energy generator. Here, abnormality diagnosis can be performed through statistical inference of the current power generation data 110 and the past power generation data 120 based on the pseudo-day search 130, which will be described in detail later with reference to FIGS. 4 to 9.

In one embodiment, the monitoring system 140 can monitor in real time whether there is an abnormality in the renewable energy generator. Here, the monitoring system 140 may perform a role of detecting and notifying abnormalities to the information processing system that diagnoses abnormalities in the renewable energy generator. In one embodiment, the monitoring system 140 may acquire current power generation data 110 of a renewable energy generator for real-time monitoring. The current power generation data obtained in this way may be stored as past power generation data 120 in a database (not shown) as the current time changes. Then, the monitoring system 140 may determine whether the renewable energy generator is abnormal based on statistical inference based on the current power generation data 110 and past power generation data obtained in real time. Here, the monitoring system 140 uses the similar day search 130 to determine the abnormality based on the past power generation data on a date (i.e. similar day) that has similar data that can be statistically tested with the current power generation data among the past power generation data. You can determine whether or not. Additionally, when the monitoring system 140 detects an abnormality in the renewable energy generator, it can send a notification to the worker's user terminal (or display output capable device, etc.).

In this way, the monitoring system 140 acquires the current power generation data 110 of the renewable energy generator in real time and statistically verifies it with the past power generation data 120, so that it can quickly and accurately determine whether the renewable energy generator is abnormal. . Accordingly, the operation rate of renewable energy generators can be improved and unnecessary maintenance costs due to inaccurate diagnosis can be reduced.

Figure 2 is a schematic diagram showing a configuration in which the information processing system 230 is connected to enable communication with a plurality of user terminals in order to diagnose abnormalities in a renewable energy generator according to an embodiment of the present disclosure. In one embodiment, the information processing system 230 includes one or more server devices and/ Alternatively, it may include a database, or one or more distributed computing devices and/or distributed databases based on cloud computing services. For example, the information processing system 230 may include separate systems (eg, servers) for diagnosing abnormalities in renewable energy generators.

The abnormality diagnosis system for the renewable energy generator provided by the information processing system 230 may be provided to the user through an application installed on each of the plurality of user terminals 210_1, 210_2, and 210_3.

A plurality of user terminals 210_1, 210_2, and 210_3 may communicate with the information processing system 230 through the network 220. The network 220 may be configured to enable communication between a 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, for example, a wired network such as Ethernet, a wired home network (Power Line Communication), a telephone line communication device, and RS-serial communication, a mobile communication network, a wireless LAN (WLAN), It may consist of wireless networks such as Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. The communication method is not limited, and includes communication methods that utilize communication networks that the network 220 may include (e.g., mobile communication networks, wired Internet, wireless Internet, broadcasting networks, satellite networks, etc.) as well as user terminals (210_1, 210_2, 210_3) ) may also include short-range wireless communication between

In Figure 2, the mobile phone terminal 210_1, tablet terminal 210_2, and PC terminal 210_3 are shown as examples of user terminals, but they are not limited thereto, and the user terminals 210_1, 210_2, and 210_3 use wired and/or wireless communication. It can be any computing device capable of this and on which applications, etc. can be installed and executed. For example, user terminals include smartphones, mobile phones, navigation devices, computers, laptops, digital broadcasting terminals, PDAs (Personal Digital Assistants), PMPs (Portable Multimedia Players), tablet PCs, game consoles, and wearable devices ( It may include wearable devices, IoT (internet of things) devices, VR (virtual reality) devices, AR (augmented reality) devices, etc. In addition, in Figure 2, three user terminals (210_1, 210_2, 210_3) are shown as communicating with the information processing system 230 through the network 220, but this is not limited to this, and a different number of user terminals are connected to the network ( It may be configured to communicate with the information processing system 230 through 220).

In one embodiment, the information processing system 230 may determine whether the renewable energy generator is abnormal and provide the determination to the user terminals 210_1, 210_2, and 210_3. In FIG. 2, the information processing system 230 is described as diagnosing abnormalities in a renewable energy generator, but the information processing system 230 is not limited thereto. For example, the user terminals 210_1, 210_2, and 210_3 can directly determine whether there is a problem with the renewable energy generator.

Figure 3 is a block diagram showing the internal configuration of the user terminal 210 and the 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 an abnormality diagnosis application for a renewable energy generator and capable of wired/wireless communication, for example, the mobile phone terminal 210_1 of FIG. 2, a tablet terminal ( 210_2), a PC terminal (210_3), etc. As shown, the user terminal 210 may include a memory 312, a processor 314, a communication module 316, and an input/output interface 318. Similarly, information processing system 230 may include memory 332, processor 334, communication module 336, and input/output interface 338. As shown in FIG. 3, the user terminal 210 and the information processing system 230 are configured to communicate information and/or data through the network 220 using respective communication modules 316 and 336. It can be. Additionally, the input/output device 320 may be configured to input information and/or data to the user terminal 210 through the input/output interface 318 or to output information and/or data generated from the user terminal 210.

Memories 312 and 332 may include any non-transitory computer-readable recording medium. According to one embodiment, the memories 312 and 332 are non-permanent mass storage devices such as read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. It can be included. As another example, non-perishable mass storage devices such as ROM, SSD, flash memory, disk drive, etc. may be included in the user terminal 210 or the information processing system 230 as a separate persistent storage device that is distinct from memory. Additionally, the memories 312 and 332 may store an operating system and at least one program code (eg, code for an application related to abnormal diagnosis of a renewable energy generator, etc.).

These software components may be loaded from a computer-readable recording medium separate from the memories 312 and 332. This separate computer-readable recording medium may include a recording medium directly connectable to the user terminal 210 and the information processing system 230, for example, a floppy drive, disk, tape, DVD/CD- It may include computer-readable recording media such as ROM drives and memory cards. As another example, software components may be loaded into the memories 312 and 332 through the communication modules 316 and 336 rather than computer-readable recording media. For example, at least one program is a computer program (e.g., abnormality diagnosis of a renewable energy generator) installed by files provided through the network 220 by developers or a file distribution system that distributes installation files of the application. It may be loaded into the memories 312 and 332 based on the application associated with it, etc.).

The processors 314 and 334 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to the processors 314 and 334 by memories 312 and 332 or communication modules 316 and 336. For example, the processors 314 and 334 may be configured to execute instructions received according to program codes stored in a recording device such as the memory 312 and 332.

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 through the network 220, and may provide a configuration or function for the user terminal 210 and/or information processing. The system 230 may provide a configuration or function for communicating with other user terminals or other systems (for example, a separate cloud system, etc.). For example, a request or data generated by the processor 314 of the user terminal 210 according to a program code stored in a recording device such as the memory 312 (for example, a request for abnormality diagnosis of a renewable energy generator, etc.) It may be transmitted to the information processing system 230 through 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 is transmitted through the communication module 316 of the user terminal 210 through the communication module 336 and the network 220. It may be received by the user terminal 210. For example, the user terminal 210 may receive information about whether or not the renewable energy generator is abnormal and its abnormal status from the information processing system 230.

The input/output interface 318 may be a means for interfacing with the input/output device 320. As an example, input devices may include devices such as cameras, keyboards, microphones, mice, etc., including audio sensors and/or image sensors, and output devices may include devices such as displays, speakers, haptic feedback devices, etc. You can. As another example, the input/output interface 318 may be a means for interfacing with a device that has components or functions for performing input and output, such as a touch screen, integrated into one. In FIG. 3 , the input/output device 320 is shown not to be included in the user terminal 210, but the present invention is not limited to this and may be configured as a single device with the user terminal 210. Additionally, the input/output interface 338 of the information processing system 230 may be connected to the information processing system 230 or means for interfacing with a device (not shown) for input or output that the information processing system 230 may include. It can be. In FIG. 3, the input/output interfaces 318 and 338 are shown as elements configured separately from the processors 314 and 334, but the present invention is not limited thereto, and the input/output interfaces 318 and 338 may be configured to be included in the processors 314 and 334. there is.

The user terminal 210 and information processing system 230 may include more components than those in FIG. 3 . However, there is no need to clearly show most prior art components. In one embodiment, the user terminal 210 may be implemented to include at least some of the input/output devices 320 described above. Additionally, the user terminal 210 may further include other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, and a database. For example, if the user terminal 210 is a smartphone, it may include components generally included in a smartphone, such as an acceleration sensor, a gyro sensor, a microphone module, a camera module, and various physical devices. Various components such as buttons, buttons using a touch panel, input/output ports, and vibrators for vibration may be implemented to be further included in the user terminal 210.

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 diagnosis of abnormalities in a renewable energy generator. At this time, the program code associated with the application may be loaded into the memory 312 of the user terminal 210. While the application is operating, the processor 314 of the user terminal 210 receives information and/or data provided from the input/output device 320 through the input/output interface 318 or the information processing system ( Information and/or data may be received from 230), and the received information and/or data may be processed and stored in the memory 312. Additionally, such information and/or data may be provided to information processing system 230 via communication module 316.

While the application is running, the processor 314 inputs or selects voice data, text, and images through input devices such as a touch screen, keyboard, camera including an audio sensor and/or an image sensor, and a microphone connected to the input/output interface 318. , video, etc. can be received, and the received voice data, text, image and/or video, etc. are stored in the memory 312 or provided to the information processing system 230 through the communication module 316 and the network 220. can do. In one embodiment, the processor 314 receives user input through an input device and sends data/requests corresponding to the received user input to the information processing system 230 through the network 220 and communication module 316. ) can be provided.

The processor 314 of the user terminal 210 may transmit information and/or data to the input/output device 320 through the input/output interface 318 and output the information. For example, the processor 314 of the user terminal 210 processes information through the output device 320, such as a display output capable device (e.g., touch screen, display, etc.), an audio output capable device (e.g., speaker), etc. and/or data may be output. In one embodiment, the processor 314 may display an abnormal state of the renewable energy generator on the display of the user terminal 210.

The processor 334 of the information processing system 230 may be configured to manage, process, and/or store information and/or data received from a plurality of user terminals 210 and/or a plurality of external systems. Information and/or data processed by processor 334 may be provided to user terminal 210 through communication module 336 and network 220. In one embodiment, the processor 334 of the information processing system 230 reports the abnormal state of the renewable energy generator to the communication module 336 and the It can be provided to the user terminal 210 through the network 220.

Figure 4 is a block diagram showing a similar date search 130 and similar date determination 450 method according to an embodiment of the present disclosure. As described above with reference to FIG. 1 , abnormality diagnosis of a renewable energy generator may be performed through statistical inference of current power generation data 110 and past power generation data 120 based on similar day search 130. Specifically, the processors 314 and 334 may acquire data (e.g., electrical signal data, weather observation data, etc.) related to the current power generation amount and search for similar days in the past showing similar data. Then, the processor can determine whether there is an abnormality in the generator by statistically testing the power generation data of the corresponding similar day and the current power generation data.

Renewable energy generators can be dominated by meteorological phenomena. For this reason, the diagnosis of abnormalities in renewable energy generators is performed not only on the electrical signals of the generator (e.g., current, voltage, etc.), but also on data related to meteorological phenomena (e.g., solar radiation, wind speed, wind direction, temperature, barometric pressure, clouds, air, etc.). Density, etc.) can be considered to accurately determine whether an abnormality exists.

In one embodiment, the processor performs a similar day search 130 based on the current electrical signal data 410, current weather observation data 420, past electrical signal data 430, and past weather observation data 440. A similar date can be determined (450). Here, the electrical signal data 410 and 430 may include sub-electrical signal data such as voltage, current, and temperature obtained from generator components (eg, inverter, module, etc.). In addition, the weather observation data 420, 440 is collected/collected by a weather sensor placed near a renewable energy generator, and includes solar radiation, wind speed, wind direction, temperature, barometric pressure, clouds, air density, etc. obtained by a weather satellite. May include sub-meteorological observation data.

In one embodiment, the weather observation data 420 and 440 obtained for each type of renewable energy generator (eg, solar power generator, wind power generator, etc.) may be different. For example, from a solar power generator, horizontal solar radiation, vertical solar radiation, temperature, clouds, etc. can be obtained as weather observation data. As another example, wind speed, wind direction, air density, temperature, barometric pressure, etc. can be obtained as weather observation data from a wind power generator.

The processor may perform a similarity search 130 by calculating the degree of similarity between data based on the acquired data. In one embodiment, the processor may combine current electrical signal data 410 and current weather observation data 420 acquired over the past 24 hours or over the past 24 hours from the current point in time or over the course of a day (in the same time frame as the current data). Similarity between past electrical signal data 430 and past weather observation data 440 acquired during the day can be calculated. Here, the similarity can be calculated using a similarity measurement algorithm such as Gower's Distance, Cosine Distance, Euclidean Distance, and Pearson's Correlation Coefficient. Specifically, Gower similarity can be used when a dataset contains a mixture of continuous and discrete variables, and cosine similarity can be used when grouping multidimensional data sets, but is not limited to this.

In one embodiment, similarity may be calculated for each sub-electrical signal data and sub-meteorological observation data. For example, the similarity between the current value for the current 24 hours (current sub-electrical signal data) and the current value for the same time period in the past date (past sub-electrical signal data) may be calculated. In a similar manner, the degree of similarity between each sub-electrical signal data such as voltage and temperature can be calculated. The plurality of similarities calculated in this way may constitute a first set of similarities.

As another example, the similarity between the current wind speed value (current sub-weather observation data) and the past wind speed value (past weather observation signal data) may be calculated. In a similar manner, the similarity between each sub-meteorological observation data such as solar radiation, wind direction, temperature, barometric pressure, clouds, and air density can be calculated. The plurality of similarities calculated in this way may constitute a second set of similarities.

In one embodiment, the third set of similarities may be calculated based on the weights of each of the plurality of similarities included in the first set of similarities and the second set of similarities. Here, the third set of similarities may refer to a set of final similarities in which the respective weights of sub-electrical signal data and sub-meteorological observation data acquired during a predetermined period (24 hours, days, etc.) are considered. The weight can be calculated by quantifying the explanatory power (Explainability) of each variable using XAI (eXplainable Artificial Intelligence), which is described in detail later with reference to FIG. 9.

Based on the similarity of the third set calculated in this way, the processor may determine at least one similarity date for diagnosing an abnormality in the renewable energy generator (450). In one embodiment, the processor may determine the date of the third set of similarities having a value less than a predetermined threshold as the similarity date. In this case, a plurality of pseudo-dates can be determined, and the more pseudo-dates are determined, the better the statistical power based on the data. Details of the above-described similar date determination 450 will be described in detail with reference to FIGS. 5, 8, and 9.

Figure 5 is a block diagram showing the internal configuration of the processor 500 according to an embodiment of the present disclosure. Here, the processor 500 may be the processor 334 of an information processing system or the processor 314 of a user terminal. As shown, the processor 500 may include an information acquisition unit 510, a similarity calculation unit 520, a similarity date determination unit 530, a data processing unit 540, an abnormality diagnosis unit 550, etc. . Additionally, the processor 500 may be comprised of a single or multiple processors.

The information acquisition unit 510 may acquire power generation data and data related to the power generation amount. In one embodiment, the information acquisition unit 510 may acquire data related to power generation (eg, sub-electrical signal data and sub-meteorological observation data). For example, the information acquisition unit 510 may acquire current temperature data collected by a weather sensor placed near the solar power generator. Specifically, temperature data for 24 hours prior to the current time can be obtained as current temperature data (for example, temperature data between 12:00 on May 9, 2023, and 11:00 on May 10, 2023). Likewise, the information acquisition unit 510 may acquire past temperature data collected by a weather sensor placed near the solar power generator. Specifically, temperature data (in the same time zone as the current temperature data) for all past days can be obtained as historical temperature data (for example, from 12:00 to 11:00 for past dates before May 9, 2023). temperature data between).

In this way, the information acquisition unit 510 can acquire weather observation data (e.g., sub-meteorological observation data such as solar radiation, wind speed, wind direction, temperature, barometric pressure, clouds, and air density) acquired by a weather satellite. You can. In a similar manner, the information acquisition unit 510 may acquire sub-electrical signal data such as voltage, current, and temperature obtained from generator components (eg, inverter, module, etc.).

In one embodiment, the information acquisition unit 510 may acquire power generation data 110 and 120 of a renewable energy generator. For example, the information acquisition unit 510 may obtain current power generation data of the solar power generator. As another example, the information acquisition unit 510 may acquire past power generation data of a wind power generator.

The power generation data and data related to the power generation obtained as described above may be provided to the similarity calculation unit 520 to calculate each similarity, or may be provided to the data processing unit 540 to convert them into a form suitable for analysis. Alternatively, it may be stored in a database (not shown).

The similarity calculation unit 520 may calculate the similarity (distance) between each of the acquired current data and past data. Specifically, the similarity calculation unit 520 may calculate a first set of similarities from a plurality of sub-electrical signal data and a second set of similarities from a plurality of sub-meteorological observation data. In this case, the above-described similarity measurement algorithm can be used, and the smaller the similarity value, the more similar it can be determined. However, this is not limited to this, and the decision criteria may be different for each algorithm.

The similarity calculation unit 520 may calculate the final similarity for each date based on the calculated similarity of the first set and the similarity of the second set. The final similarity for each date calculated in this way can constitute a third set of similarity. Here, the final similarity is calculated using the weight of each similarity, which is described in detail later with reference to FIG. 9. The third set of similarities calculated in this way may be provided to the similar date determination unit 530 or stored in a database to determine the similar date.

The pseudo-day determination unit 530 may determine the pseudo-day based on the third set of similarities for a statistical test for diagnosing a generator abnormality. In one embodiment, the similarity date determination unit 530 may determine, among the third set of similarities, a date whose similarity does not exceed a predetermined threshold as a similarity date. In other words, a plurality of similar days can be determined, and the more similar days there are, the better the statistical power can be. In another embodiment, the pseudo-day determination unit 530 may determine the pseudo-date based on a threshold inferred using a machine learning model, rather than a predetermined threshold.

The similar date determined as described above may be provided to the abnormality diagnosis unit 550 for statistical testing for abnormality diagnosis, may be provided to the data processing unit 540 for conversion to be suitable for analysis, or may be stored in a database.

The power generation data may include current sub-generation data and a plurality of past sub-generation data.

The data processing unit 540 may use the acquired pseudo-day to extract past sub-generation amount data related to the pseudo-day from a plurality of past sub-generation amount data. Here, the past sub-generation data associated with the similar day may include past sub-generation data in the same time period as the current power generation data on the similar day. Then, the data processing unit 540 may transform the data so that the past sub-generation data associated with the similar day follows a normal distribution (or t-distribution) for a two-sided test. For example, since power generation data is a physical quantity that only has positive values, its distribution can be checked by performing log transformation, etc., and data with a specific time resolution can be analyzed through accumulation or average.

The data processing unit 540 can convert weather observation data and use it for similar day search or statistical analysis. In one embodiment, the data processing unit 540 can convert data collected by a weather sensor into a value with the same specific time resolution as the power generation data, or derive average, accumulation, deviation, etc. and use it for analysis. there is. In another embodiment, the data processing unit 540 does not use the data acquired by the meteorological satellite for analysis as it is because it is like a continuous image, but treats it as spatio-temporal data, converts it, and then analyzes it. there is. In addition, the data processing unit 540 may extract values from weather observation data as coordinates of an area of interest, use an inverse distance weighting method, or derive accumulation, average, deviation, etc., and use the converted meteorological satellite data for analysis. This is described in detail later with reference to FIGS. 6 and 7.

Data converted to follow a normal distribution (or t-distribution) or data converted to be suitable for similar date search or analysis are provided to the similarity calculation unit 520, the similar date determination unit 530, and the abnormality diagnosis unit 550. It can be stored in a database.

The abnormality diagnosis unit 550 can derive a probability distribution from the converted past sub-generation data of similar days. Then, the abnormality diagnosis unit 550 may determine whether there is an abnormality by performing a two-sided test on a statistical hypothesis (eg, null hypothesis). Additionally, when an abnormality in the generator is detected, the abnormality diagnosis unit 550 may notify the monitoring system of the abnormal state of the generator. Here, the abnormality diagnosis unit 550 may use the Z statistic (normal distribution) or the t statistic (t distribution), which will be described in detail later with reference to FIG. 8.

With this configuration, it is possible to quickly diagnose abnormalities in the renewable energy generator, further improve the operation rate of the renewable energy generator, and reduce maintenance costs.

Figure 6 is a block diagram showing an example of processing data acquired by a meteorological satellite according to an embodiment of the present disclosure. The Korea Meteorological Administration 610 may provide weather-related data from satellites that perform weather observation (e.g., Cheollian Satellite 2A, etc.) in NetCDF (Network Common Data Form; .nc file) format. In one embodiment, the processor 500 may receive (620) the original NetCDF data file from the Korea Meteorological Administration (610) in order to diagnose an abnormality in the generator.

Since the original NetCDF data received in this way is like a large continuous image, it may be required to treat and convert it into spatiotemporal data. In one embodiment, the processor 500 may extract 2D matrix data (630) from the original NetCDF data file. Then, satellite data near the area of interest can be extracted (640). For example, data near the area of interest can be extracted using the latitude and longitude coordinates of the area of interest to be analyzed. Then, satellite data for the area of interest can be calculated (650). Here, data on the area of interest can be calculated using the inverse distance weighting method, which is one of the spatial interpolation methods.

As described above, by diagnosing an abnormality in a renewable energy generator based on processed weather observation data, a more accurate determination of abnormality can be made.

FIG. 7 is a diagram illustrating an example of processing data acquired by a meteorological satellite according to an embodiment of the present disclosure. An example of processing weather observation data explained using FIG. 6 will be described below using specific images and formulas in FIG. 7.

In one embodiment, the original NetCDF data file 710 received from the National Weather Service 610 may not have data from the exact location (area of interest, 722) to be analyzed, but instead contains data 720 in the vicinity of the area of interest. It can be included. Accordingly, the processor 500 may first extract data 720 near the area of interest.

Then, processor 500 may use spatial interpolation to obtain data on the region of interest. For example, the processor 500 may use an inverse distance weighting method. Here, Inverse Distance Weighting (IDW) is one of the spatial interpolation methods based on geographical space. It calculates the value of the interpolation point by weighting it in inverse proportion to the distance of the interpolation point using the value of the already known coordinates. It can refer to an interpolation method. The processor 500 can extract the optimal data value in the region of interest 722 from the data 720 near the region of interest using Equation 1 below.

In Equation 1, Zj may represent the optimal value of the reference grid line, wi may represent the inverse distance weight of the i-th data point, Zi may represent the value of the i-th data point, and N may represent the number of data points.

The above-mentioned spatial interpolation method is not limited to the inverse distance weighting method, but also includes TIN (irregular triangle) interpolation, Regularized Splines with Tension (RST), Kriging, or Trend Surface interpolation. can be used

FIG. 8 is a diagram illustrating an example of diagnosing an abnormality in a generator through statistical inference according to an embodiment of the present disclosure. The processor 500 may perform statistical inference based on past sub-generation data and current sub-generation data of similar days to diagnose an abnormality in the generator. In one embodiment, the processor 500 may determine whether there is an abnormality by performing a two-sided test on the null hypothesis that there is no difference between the current data (μ) and the past data (μ ₀ ) (μ=μ ₀ ).

In one embodiment, the processor 500 may use the Z statistic (normal distribution) or the t statistic (t distribution) for statistical inference. For example, the processor 500 may transform the data so that past sub-generation data and current sub-generation data of similar days follow a normal distribution (or t-distribution). Then, the processor 500 can derive a probability distribution from the converted past sub-generation data of similar days.

In one embodiment, the processor 500 may determine whether the generator is abnormal according to a two-tailed test from the derived probability distribution. Here, the two-sided test may refer to a method of testing the probability distribution by dividing it into an acceptance region (810) and both rejection regions (820) according to a set significance level (α). For example, when the current sub-generation data exceeds a set significance level and is included in the rejection region of the probability distribution of past sub-generation data, the processor 500 may notify the monitoring system of an abnormality in the generator.

In one embodiment, the significance level may be a predetermined value, and in another embodiment, the significance level may be a value inferred by a machine learning model.

Figure 9 is a diagram illustrating an example of determining a similar date by considering a weight of similarity according to an embodiment of the present disclosure. The processor 500 may calculate the final similarity based on the respective weights of the first set of similarities and the second set of similarities.

In one embodiment, the processor 500 uses a similarity measurement algorithm to determine the electrical signal data 410 and weather observation data 420 acquired over the past 24 hours from the current point in time and the electrical signal data 420 acquired over the past 24 hours in the same time zone. Similarities (920_1 to 920_n) between the electrical signal data 430 and the weather observation data 440 can be calculated.

In one embodiment, as shown in the table, similarities 920_1 to 920_n may be calculated for each date 910 in the past. In the table shown, the similarity may include a first set of similarities 920_n and a second set of similarities 920_1 to 920_3, and a lower similarity value may indicate that the current data and past data are similar. Here, only one current similarity is shown as the first set of similarities, but this is only an example. The first set of similarities may include similarities for a plurality of sub-electrical signal data such as voltage and temperature.

In one embodiment, the final similarity may be calculated based on each weight (w _k ) of the calculated similarity (d _k ).

In Equation 2, Σw _k = 1, k = 1,2, to n.

In one embodiment, the weight (w _k ) can be calculated by quantifying the explainability of each variable using XAI (eXplainable Artificial Intelligence). Here, XAI (Explainable AI) can refer to artificial intelligence that presents the reasons for the artificial intelligence's judgment in a way that humans can understand, and through this, it overcomes the limitations of complex artificial neural networks whose operating principles are not clearly analyzed. It can be overcome. In other words, the processor 500 can use XAI to calculate the weight by quantifying the explanatory power of each variable for power generation.

The processor 500 may use Local Interpretable Model-agnostic Explanations (LIME), Partial Dependence Plots (PDP), and SHapley Additive exPlanations (SHAP) as XAI techniques. Specifically, LIME creates an interpretable surrogate model (e.g., a linear model) using the prediction results of the AI model in the local area of the decision boundary, and can derive explanatory power by measuring the similarity between the AI and the surrogate model. there is. PDP can derive explanatory power by treating input variables excluding specific input variables as constants and calculating partial dependence by calculating predicted values. SHAP can derive explanatory power using the shapley value of each input variable (calculating the marginal contribution of the input variable to the predicted value).

In one embodiment, the processor 500 may calculate each final similarity for each date in the past using Equation 2 above. The final similarity (values in column 930) for each date calculated in this way can constitute a third set of similarity.

In one embodiment, the processor 500 may determine a date with a similarity that does not exceed a predetermined threshold among the similarities in the third set as a similarity date. For example, the processor 500 may determine a date with a similarity that does not exceed the threshold of 0.3 as a similar date. The table shown in FIG. 9 may indicate that when the threshold is 0.3, the final similarity that satisfies this threshold is sorted in ascending order. Here, the processor 500 may determine each date (e.g., April 23, 2023, May 10, 2022, ??, May 1, 2023) of the final similarity 930 as a similarity date. there is.

Figure 10 is an exemplary diagram showing an artificial neural network model 1000 according to an embodiment of the present disclosure. The artificial neural network model 1000 is an example of a machine learning model, and in machine learning technology and cognitive science, it is a statistical learning algorithm implemented based on the structure of a biological neural network or a structure that executes the algorithm.

According to one embodiment, the artificial neural network model 1000 has nodes, which are artificial neurons that form a network through the combination of synapses, as in a biological neural network, repeatedly adjusting the weights of synapses to determine the correct input corresponding to a specific input. By learning to reduce the error between the output and the inferred output, a machine learning model with problem-solving capabilities can be represented. For example, the artificial neural network model 1000 may include a random probability model, a neural network model, etc. used in artificial intelligence learning methods such as machine learning and deep learning.

According to one embodiment, a model for diagnosing abnormalities in the above-described renewable energy generator or a model for calculating weights used when deriving the final similarity may be created in the form of an artificial neural network model 1000. For example, the artificial neural network model 1000 may receive electrical signal data, weather observation data, and power generation data of a renewable energy generator, and estimate whether the generator is abnormal based on this.

The artificial neural network model 1000 is implemented as a multilayer perceptron (MLP) consisting of multiple layers of nodes and connections between them. The artificial neural network model 1000 according to this embodiment can be implemented using one of various artificial neural network model structures including MLP. As shown in FIG. 4, the artificial neural network model 1000 includes an input layer 1020 that receives an input signal or data 1010 from the outside, and an output layer that outputs an output signal or data 1050 corresponding to the input data. (1040), located between the input layer 1020 and the output layer 1040, receives a signal from the input layer 1020, extracts the characteristics, and transmits it to the output layer 1040. n (where n is a positive integer) It consists of hidden layers (1030_1 to 1030_n). Here, the output layer 1040 receives signals from the hidden layers 1030_1 to 1030_n and outputs them to the outside.

The learning method of the artificial neural network model (1000) includes a supervised learning method that learns to optimize problem solving by inputting a teacher signal (correct answer), and an unsupervised learning method that does not require a teacher signal. ) There is a way. According to one embodiment, the information processing system may learn the artificial neural network model 1000 using power generation data of a renewable energy generator, weather observation data, and electrical signal data.

According to one embodiment, the information processing system may directly generate learning data for training the artificial neural network model 1000. For example, the information processing system may generate a learning data set that includes power generation data from a renewable energy generator, weather observation data, and electrical signal data. Then, the information processing system can learn an artificial neural network model 1000 to diagnose an abnormality in the generator, calculate a weight, or calculate a similar date based on the generated learning data set.

According to one embodiment, input variables of the artificial neural network model 1000 may include hourly power generation data, weather observation data, and electrical signal data. In this way, when the above-described input variables are input through the input layer 1020, the output variables output from the output layer 1040 of the artificial neural network model 1000 may be whether the generator is abnormal, a weight, or a similar event.

In this way, a plurality of input variables and a plurality of output variables corresponding to the input layer 1020 and the output layer 1040 of the artificial neural network model 1000 are matched, respectively, and the input layer 1020, the hidden layers 1030_1 to 1030_n, and By adjusting the synapse values between nodes included in the output layer 1040, learning can be done so that the correct output corresponding to a specific input can be extracted. Through this learning process, the characteristics hidden in the input variables of the artificial neural network model (1000) can be identified, and the nodes of the artificial neural network model (1000) can be used to reduce the error between the output variables calculated based on the input variables and the target output. You can adjust the synapse values (or weights) between them. In addition, the information processing system learns an algorithm that receives hourly power generation data, weather observation data, and electrical signal data as input, and can learn in a way to minimize loss with expected diagnosis results (i.e., annotation information).

Using the artificial neural network model 1000 learned in this way, it can be estimated whether the renewable energy generator is abnormal.

Figure 11 is a flowchart showing a method for diagnosing abnormalities in a renewable energy generator according to an embodiment of the present disclosure. The pseudo-day search-based renewable energy generator abnormality diagnosis method 1100 may be initiated by at least one processor acquiring electrical signal data of the renewable energy generator (S1110). In one embodiment, the processor may acquire current electrical signal data. Alternatively or additionally, the processor may obtain historical electrical signal data. Here, the electrical signal data may include data such as voltage, current, and temperature obtained from generator components (eg, inverter, module, etc.).

Afterwards, the processor may acquire weather observation data (S1120). In one embodiment, the processor may acquire weather observation data such as horizontal solar radiation, vertical solar radiation, temperature, and clouds as sub-weather observation data to diagnose abnormalities in the solar power generator. In another embodiment, the processor may acquire weather observation data such as wind speed, wind direction, air density, temperature, and barometric pressure as sub-weather observation data to diagnose abnormalities in the wind power generator. Here, the weather observation data may include at least one of data collected by a weather sensor placed near the generator or data acquired by a weather satellite.

In one embodiment, the processor may transform the acquired weather observation data to be suitable for analysis. For example, the processor can convert data collected by a weather sensor placed near a generator into values with a specific time resolution, or derive the average, accumulation, and deviation of the collected data and use it for analysis. . As another example, the processor may treat data acquired by a weather satellite as spatiotemporal data, convert it, and then analyze it.

Subsequently, the processor may obtain power generation data of the renewable energy generator (S1130). The power generation data may include current sub-generation data and a plurality of past sub-generation data. In one embodiment, the processor may obtain current sub-generation data. Alternatively or additionally, the processor may obtain historical sub-generation data.

In one embodiment, the processor may transform the obtained power generation data to follow a normal distribution (or t-distribution). The processor can check the distribution by squaring the power generation data or performing logarithmic transformation, and data with a specific time resolution can be used for analysis through accumulation or averaging.

Thereafter, the processor may diagnose abnormalities in the renewable energy generator based on electrical signal data, weather observation data, and power generation data (S1140). In one embodiment, the processor may calculate the similarity between current data and past data for each of the acquired electrical signal data and weather observation data. Then, the processor can calculate the final similarity using the weight of each similarity. Here, the weight can be determined using XAI. Then, the processor can determine the similarity date based on the calculated final similarity. The processor can perform statistical inference based on the power generation data of the similar date and the current power generation data determined in this way, and through this, can diagnose whether there is an abnormality in the generator.

In one embodiment, the step of diagnosing an abnormality in a renewable energy generator includes determining at least one similarity date by calculating the similarity between past electrical signal data and past observation data, and current electrical signal data and current weather observation data. , It may include deriving a power generation data probability distribution based on data associated with at least one similar day among past power generation data and diagnosing an abnormality in the renewable energy generator based on the power generation data probability distribution and current power generation data.

In one embodiment, the step of diagnosing an abnormality in the renewable energy generator includes calculating a first set of similarities between the current sub-electrical signal data and each of the plurality of past sub-electrical signal data, the current sub-meteorological observation data and the plurality of past sub-electrical signal data. It may include calculating a second set of similarities between each of the past sub-meteorological observation data and determining at least one similar date based on the first set of similarities and the second set of similarities.

In one embodiment, determining at least one similar date includes calculating a third set of similarities by applying weights to each of the first set of similarities and the second set of similarities, and calculating the third set of similarities. It may include determining at least one similar date based on the method.

In one embodiment, the step of diagnosing an abnormality in a renewable energy generator includes extracting at least one past sub-generation data associated with at least one similar date among a plurality of past sub-generation data, and at least one past sub-generation data and the current It may include diagnosing an abnormality in the renewable energy generator based on sub-generation data.

In one embodiment, the step of diagnosing an abnormality in a renewable energy generator includes processing at least one past sub-generation data to follow a normal distribution, and performing statistical inference based on the processed past power generation data and current sub-generation data. It may include the step of diagnosing an abnormality in the renewable energy generator based on the step and statistical inference results.

The flowchart shown in FIG. 11 and the above description are only examples and may be implemented differently in some embodiments. For example, in some embodiments, the order of each step may be changed, some steps may be performed repeatedly, some steps may be omitted, or some steps may be added.

The above-described method may be provided as a computer program stored in a computer-readable recording medium for execution on a computer. The medium may continuously store a computer-executable program, or may temporarily store it for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may 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 there may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

The methods, operations, or techniques of this disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchange of hardware and software, 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 specific application and design requirements imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementations should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques may include 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, and other electronic units designed to perform the functions described in this disclosure. , a computer, or a combination thereof.

Accordingly, the various illustrative logical blocks, modules, and circuits described in connection with this disclosure may be general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed as any combination of those designed to perform the functions described in. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other configuration.

For firmware and/or software implementations, techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), and PROM ( on computer-readable media such as programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. It can also be implemented with stored instructions. Instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described in this disclosure.

Although the above-described embodiments have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the disclosure is not limited thereto and may also be implemented in conjunction with any computing environment, such as a network or distributed computing environment. . Furthermore, aspects of the subject matter of this disclosure may be implemented in multiple processing chips or devices, and storage may be similarly effected across the multiple devices. These devices may include PCs, network servers, and portable devices.

Although the present disclosure has been described in relation to some embodiments in this specification, various modifications and changes may be made without departing from the scope of the present disclosure as can be understood by a person skilled in the art to which the invention pertains. Additionally, such modifications and changes should be considered to fall within the scope of the claims appended hereto.

110: Current power generation data
120: Past power generation data
130: Search for similar days
140: monitoring system

Claims (10)

In the pseudo-day search-based renewable energy generator abnormality diagnosis method performed by at least one processor,
Obtaining electrical signal data from a renewable energy generator;
Obtaining meteorological observation data;
Obtaining power generation data of the renewable energy generator; and
Diagnosing an abnormality in the renewable energy generator based on the electrical signal data, the weather observation data, and the power generation data.
Including,
The power generation data includes past power generation data and current power generation data,
The electrical signal data includes sub-electrical signal data obtained from a plurality of components of the generator,
The electrical signal data includes current sub-electrical signal data and a plurality of past sub-electrical signal data,
The weather observation data includes current sub-weather observation data and a plurality of past sub-weather observation data,
The step of diagnosing an abnormality in the renewable energy generator is,
calculating a first set of similarities between the current sub-electrical signal data and each of the plurality of past sub-electrical signal data,
Calculating a second set of similarities between the current sub-meteorological observation data and each of the plurality of past sub-meteorological observation data,
determining at least one similarity date based on the first set of similarities and the second set of similarities, and
Diagnosing an abnormality in the renewable energy generator based on data related to the at least one similar day among the past power generation data and the current power generation data
Including,
Each of the first set similarity and the second set similarity is calculated using at least one of Gower similarity, cosine similarity, Euclidean distance, and Pearson correlation coefficient.
According to paragraph 1,
The weather observation data includes at least one of data collected by a weather sensor disposed near the renewable energy generator or data acquired by a weather satellite,
How to diagnose problems with renewable energy generators.
According to paragraph 1,
The step of diagnosing an abnormality in the renewable energy generator is,
Deriving a probability distribution of power generation data based on data associated with the at least one similar day among the past power generation data; and
Diagnosing an abnormality in the renewable energy generator based on the power generation data probability distribution and the current power generation data
A method for diagnosing abnormalities in a renewable energy generator, further comprising:

delete According to paragraph 1,
Determining at least one similar date based on the first set of similarities and the second set of similarities includes:
calculating a third set of similarities by applying weights to each of the first and second sets of similarities; and
determining the at least one similarity date based on the third set of similarities.
Including, a method for diagnosing abnormalities in a renewable energy generator.
According to paragraph 1,
The power generation data includes current sub-generation data and a plurality of past sub-generation data,
Diagnosing an abnormality in the renewable energy based on data related to the at least one similar day among the past power generation data and the current power generation data,
Extracting at least one past sub-generation amount data associated with the at least one similar date from among the plurality of past sub-generation amount data; and
Diagnosing an abnormality in the renewable energy generator based on the at least one past sub-generation data and current sub-generation data
Including, a method for diagnosing abnormalities in a renewable energy generator.
According to clause 5,
The weight is determined using XAI (eXplanable AI), a renewable energy generator abnormality diagnosis method.
According to clause 6,
Diagnosing an abnormality in the renewable energy based on data related to the at least one similar day among the past power generation data and the current power generation data,
Processing the at least one past sub-generation data to follow a normal distribution;
performing statistical inference based on the processed past power generation data and the current sub-generation data; and
Diagnosing an abnormality in the renewable energy generator based on the statistical inference results
A method for diagnosing abnormalities in a renewable energy generator, further comprising:
A computer program stored in a computer-readable recording medium for executing the method according to any one of claims 1 to 3 and 5 to 8 on a computer.
As an information processing system,
communication module;
Memory; and
At least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory
Including,
The at least one program is,
Acquire electrical signal data from renewable energy generators,
Obtain meteorological observation data,
Obtain power generation data of the renewable energy generator,
It includes diagnosing an abnormality in the renewable energy generator based on the electrical signal data, the weather observation data, and the power generation data,
The power generation data includes past power generation data and current power generation data,
The electrical signal data includes sub-electrical signal data obtained from a plurality of components of the generator,
The electrical signal data includes current sub-electrical signal data and a plurality of past sub-electrical signal data,
The weather observation data includes current sub-weather observation data and a plurality of past sub-weather observation data,
Diagnosing abnormalities in the renewable energy generator,
Calculating a first set of similarities between the current sub-electrical signal data and each of the plurality of past sub-electrical signal data,
Calculate a second set of similarities between the current sub-meteorological observation data and each of the plurality of past sub-meteorological observation data,
Determine at least one similarity date based on the first set of similarities and the second set of similarities,
It includes diagnosing an abnormality in the renewable energy generator based on data related to the at least one similar day among the past power generation data,
The information processing system, wherein each of the first set similarity and the second set similarity is calculated using at least one of Gower similarity, cosine similarity, Euclidean distance, and Pearson correlation coefficient.

Images