WO2021060772A1 - Machine learning-based photovoltaic power generation operation management system and management method - Google Patents
Machine learning-based photovoltaic power generation operation management system and management method Download PDFInfo
- Publication number
- WO2021060772A1 WO2021060772A1 PCT/KR2020/012536 KR2020012536W WO2021060772A1 WO 2021060772 A1 WO2021060772 A1 WO 2021060772A1 KR 2020012536 W KR2020012536 W KR 2020012536W WO 2021060772 A1 WO2021060772 A1 WO 2021060772A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- reference pattern
- management server
- machine learning
- connection panel
- parameter
- Prior art date
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 39
- 238000010248 power generation Methods 0.000 title claims abstract description 35
- 238000007726 management method Methods 0.000 title claims description 82
- 230000005856 abnormality Effects 0.000 claims abstract description 48
- 230000007613 environmental effect Effects 0.000 claims abstract description 22
- 238000009434 installation Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 6
- 238000013480 data collection Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 229920000544 Gore-Tex Polymers 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000005494 condensation Effects 0.000 description 4
- 238000009833 condensation Methods 0.000 description 4
- 229910002092 carbon dioxide Inorganic materials 0.000 description 3
- 239000001569 carbon dioxide Substances 0.000 description 3
- 239000002803 fossil fuel Substances 0.000 description 3
- 238000001816 cooling Methods 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000010792 warming Methods 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S40/00—Components or accessories in combination with PV modules, not provided for in groups H02S10/00 - H02S30/00
- H02S40/30—Electrical components
- H02S40/34—Electrical components comprising specially adapted electrical connection means to be structurally associated with the PV module, e.g. junction boxes
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02S—GENERATION OF ELECTRIC POWER BY CONVERSION OF INFRARED RADIATION, VISIBLE LIGHT OR ULTRAVIOLET LIGHT, e.g. USING PHOTOVOLTAIC [PV] MODULES
- H02S50/00—Monitoring or testing of PV systems, e.g. load balancing or fault identification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Definitions
- the present invention relates to a machine learning-based solar power generation operation management system and management method.
- solar cells and other green energy sources have great advantages in that they do not use fossil fuels, which are limited to the earth, and that they do not emit carbon dioxide gas, so they can minimize environmental pollution.
- These advantages are global warming and fossil fuels. Considering the position of modern people who must prepare for the near future when exhaustion becomes serious, the importance of this is bound to be very high.
- Korean Patent Registration No. 10-0999978 measures a plurality of solar cell modules that convert and output solar energy into electrical energy, an inverter that converts power output from the plurality of solar cell modules, and the generated voltage and current.
- a photovoltaic power generation monitoring control device that monitors and controls the presence or absence of overvoltage, overcurrent, or reverse current in the circuit group to which each solar cell module is connected, and a switching unit that cuts off the power according to the monitoring result, and its information are received. It is characterized by consisting of a data collection and monitoring device that collects and monitors data.
- the Applicant provides a machine learning-based solar power generation operation management system that predicts changes in parameters collected in real time using a reference pattern analyzed based on machine learning, and controls the access panel when an abnormality is detected through the predicted change. I want to.
- a machine learning-based photovoltaic power generation operation management system for achieving the above object includes a solar cell including a plurality of solar cell modules, a connection panel, and the amount of sunlight of the solar cell, and It includes a management server that monitors current and humidity as parameters,
- connection panel predicts a change trend of the parameter by comparing a reference pattern for each parameter previously analyzed in consideration of the installation location and environmental factors of the solar cell with a parameter collected in real time, and a predicted inflection point extracted from the predicted change trend. And parameter information used for predicting change trends may be used as change data.
- the management server receives the change data for each parameter from the access panel, transmits a reference pattern for each parameter by analyzing the received change data for each parameter based on machine learning, to the access panel, and from the received change data
- a notification and a control signal for abnormality control may be provided to the connection panel.
- the access panel predicts the change trend for each parameter, but predicts the change trend in units of a preset interest section for the parameter collected in real time, and generates change data only when the change trend is predicted in the interest section and manages the above. Can be sent to the server.
- the management server generates a correlation model that analyzes the correlation between the sunlight amount reference pattern and the current amount reference pattern, and analyzes the correlation between the measured amount of sunlight and the measured amount of current from the change data collected in real time, and the degree of similarity with the correlation model. If is less than the preset rate, it can be judged as more than the current.
- the management server may notify the manager terminal and transmit a control signal for turning off the switch of the corresponding solar cell module determined as the current abnormality to the connection panel.
- the access panel includes a heat pump for controlling the internal humidity
- the management server controls the driving of the heat pump so that the predicted humidity analyzed from the change data collected in real time becomes the pre-analyzed reference humidity.
- a signal can be transmitted to the connection panel.
- the access panel transmits a thermal image sensor that generates a thermal image for each area by dividing the interior of the access panel, and transmits a thermal image for each area generated in real time to the management server.
- the management server may include a control unit for notifying the management server when the temperature increases compared to the reference pattern in a specific region.
- control unit of the access panel may drive a fire extinguishing unit when a fire is expected due to a sudden increase in temperature in a specific area analyzed by the generated thermal image, and may notify the occurrence of a fire to the management server.
- the management server may analyze the thermal image for each area based on machine learning, and generate a temperature reference pattern for each area in which environmental factors of the access panel are considered and transmit it to the access panel.
- a solar cell including a plurality of solar cell modules; Connection panel; And a management server for monitoring the amount of sunlight of the solar cell, current and humidity of the connection panel as parameters, the method of operating and managing a system based on photovoltaic power generation, in the connection panel, collecting the parameters in real time, the In a connection panel, predicting a change trend of the parameter by comparing a reference pattern for each parameter previously analyzed in consideration of the installation location and environmental factors of the solar cell and the parameters collected in real time, and in the connection panel, the predicted change Generating the predicted inflection point extracted from the trend and parameter information used for predicting the change trend as change data and transmitting it to the management server, the management server analyzing the change data to detect an abnormal prediction, and the management server In the case of detecting an abnormality prediction, it may include providing a control signal for abnormality control to the connection panel.
- the parameter collected in real time is predicted in units of a preset interest section, but change data can be generated and transmitted to the management server only when the change trend is predicted in the interest section. have.
- the step of detecting the abnormal prediction may include generating a correlation model that analyzes the correlation between the reference pattern of the amount of sunlight and the reference pattern of the amount of current, and by analyzing the correlation between the amount of sunlight and the amount of current measured from the change data collected in real time. If the degree of similarity with the correlation model is less than or equal to a preset rate, it can be determined as more than the current.
- a control signal for notifying the manager terminal and turning off the switch of the corresponding solar cell module determined as the current abnormality may be transmitted to the connection panel.
- control signal includes the heat pump provided in the connection panel so that the predicted humidity analyzed from the change data collected in real time becomes a pre-analyzed reference humidity.
- a control signal for controlling driving may be transmitted to the connection panel.
- connection panel when a fire is expected due to a sudden increase in temperature in a specific area analyzed by the generated thermal image, the step of driving a fire extinguishing unit and notifying the occurrence of a fire to the management server may be further included.
- the management server generating a sunlight amount reference pattern, a current reference pattern, and a humidity reference pattern by analyzing the amount of sunlight, current and humidity collected in real time by applying an environmental factor, in the management server, the thermal image for each area
- the image is analyzed based on machine learning, but may further include generating a temperature reference pattern for each region in which environmental factors are considered, and transmitting a reference pattern for each parameter to the connection panel.
- the machine learning-based photovoltaic power generation operation management system and management method of the present invention uses the reference pattern analyzed by big data in consideration of the installation location and environmental factors (time, season, shade, weather, etc.) of the solar cell. Based on this, it is possible to predict changes in parameters collected in real time and detect abnormalities.
- a notification is provided to the manager terminal, and the operation of the access panel can be controlled using a control signal.
- the fire extinguishing unit is immediately operated at the connection panel to prevent major damage from the fire, and the occurrence of reverse current can be prevented by turning off a switch in which an abnormal current is detected.
- FIG. 1 is a block diagram showing a schematic configuration of a machine learning-based solar power generation operation management system according to an embodiment of the present invention.
- FIG. 2 is a block diagram showing the configuration of the control unit of FIG. 1.
- FIG. 3 is a graph for explaining prediction of a parameter change trend according to an embodiment of the present invention.
- FIG. 4 is a block diagram showing the configuration of the management server of FIG. 1.
- FIG. 5 is a graph for explaining a correlation between a reference pattern of a change in the amount of sunlight and the amount of current according to an embodiment of the present invention.
- FIG. 6 is a graph for explaining an abnormality in a pattern of changes in the amount of sunlight and the amount of current collected in real time according to an embodiment of the present invention.
- FIG. 7 is a flowchart illustrating a method of operating and managing photovoltaic power generation based on machine learning according to an embodiment of the present invention.
- a machine learning-based photovoltaic operation management system (hereinafter referred to as a system) according to an embodiment of the present invention includes a solar cell 100, a sunlight sensor 110, a connection panel 200, a management server 300, and a DB It may include (400).
- the system of the present invention provides visually by monitoring the amount of sunlight, current amount, humidity and temperature of the connection panel 200 of the solar cell 100 as parameters during solar power generation operation, and a manager terminal when a risk factor is predicted during monitoring. You can notify (not shown).
- the system of the present invention predicts a change trend by comparing the parameter collected in real time with a reference pattern analyzed based on big data machine learning, and periodically updates the reference pattern based on this, thereby accurately predicting the change trend.
- the solar cell 100 converts light energy incident from the sun into electrical energy and outputs it.
- the solar cell 100 includes a plurality of solar cell arrays 100a to 100n.
- the solar cell array includes a plurality of solar cell modules. A number of solar cell modules, which are components of each solar cell array, are configured by being connected in series with each other.
- the amount of sunlight sensor 110 is installed on the panel of the solar cell 100 to sense the amount of sunlight at the location where the solar cell 100 is installed in real time, and the sensed amount of sunlight is controlled through the communication unit 240 of the connection panel 200. It can be transmitted to 230.
- connection panel 200 compares the amount of sunlight received in real time from the sunlight amount sensor 110, the output current received from the solar cell 100, and the humidity and temperature in the connection panel 200 with a corresponding reference pattern to determine the change trend for each parameter. It is predictable.
- the connection panel 200 includes a switch 210, a sensor unit 220, a control unit 230 (MCU), a communication unit 240, a control circuit unit 250, a heat pump 260, and a fire extinguishing unit ( 270, and the sensor unit 220 may include a current sensor 221, a humidity sensor 222, and a thermal image sensor 223.
- the connection board 200 may be packaged using a functional fiber such as Gore-Tex, and a bolt to which Gore-Tex is applied may be used even when the enclosure is combined.
- connection panel 200 when a differential pressure occurs due to a temperature change, pressure is balanced inside and outside the connection panel 200 by packaging and coupling bolts of the connection panel 200 using Gore-Tex to prevent external fluids (e.g., rain, etc.). It can prevent penetration and prevent condensation from occurring.
- Gore-Tex to prevent external fluids (e.g., rain, etc.). It can prevent penetration and prevent condensation from occurring.
- the switch 210 may receive the output power of the solar cell 100 in units of strings.
- the control circuit unit 250 may merge output power in units of strings received under the control of the controller 230 and provide them to the inverter.
- the current sensor 222 may sense the current in each string unit from the output power received in the string unit of the solar cell 100 and provide it to the controller 230.
- the humidity sensor 222 may sense the humidity in the connection panel 300 in real time and provide it to the control unit 230.
- the thermal image sensor 223 may provide the controller 230 with a thermal image obtained by capturing a thermal image in the connection panel 300 in real time.
- the thermal image may be obtained by dividing the area within the connection panel 300 into a plurality of areas and photographing each area.
- the control circuit unit 250 having a high heat generation temperature may be intensively sensed.
- the thermal image sensor 220 may divide the area of the control circuit unit 250 by circuit configuration or by a unit area to obtain a real-time thermal image for each area location of the control circuit unit 250.
- the thermal image generated in real time may be transmitted to the controller 230.
- the controller 230 may include a memory 231 and a processor 232.
- the memory 231 may receive a sensing value for each parameter sensed from each of the sensors 110 and 220. That is, the memory 231 may store the amount of sunlight, the amount of current for each string, the amount of humidity, and the thermal image for each region, and may store a reference pattern for each parameter that is updated from the management server 300 at a preset period.
- the reference pattern for each parameter is a pattern in which the amount of change of each parameter is analyzed based on big data machine learning in the management server 300, and environmental conditions such as the installation location (location, shade, etc.) of the solar cell, weather, season, time, etc. It can be analyzed in consideration of factors.
- the installation location of the solar cell may be divided into a region and a plurality of locations installed within the region, and the system of the present invention may analyze and manage parameters for each location and region for monitoring. Meanwhile, the analysis of the reference pattern for each parameter will be described in detail when the management server 300 is described.
- the processor 232 may compare the sensing value for each parameter stored in the memory 231 in real time with a reference pattern of a corresponding parameter to predict a change trend of the real-time parameter sensing value. With reference to FIG. 3, the prediction of the parameter change trend of the processor 232 will be described.
- the processor 232 may compare a pattern of parameters collected in real time (actual measurement) with a reference pattern previously stored in the memory 231.
- the pattern of the measured parameter and the reference pattern may represent a degree of change in the sensing value of the parameter sensing value over time.
- the processor 232 samples the sensing values of the parameters collected in real time in units of a preset time interval, sets an interest interval (sampled unit interval) for predicting the trend of sensing values, and sets the sensing values of the parameters in the interest interval and
- the trend of sensing values may be predicted based on the current point t1 by comparing pattern values in the corresponding interest section of the reference pattern.
- the sensing value trend prediction may use a short-term load forecasting (STLF) analysis technique.
- STLF short-term load forecasting
- the processor 232 may extract the predicted inflection point P from the predicted sensing value trend pattern through the STLF analysis method.
- the processor 232 When extracting the predicted inflection point (P), the processor 232 generates metadata including the amount of change in the sensing value and the predicted inflection point (P) in the interest section used for predicting the predicted inflection point (P) as change data, and the management server 300 ). That is, the related information may be transmitted to the management server 300 only when a change trend of a parameter according to the reference pattern is predicted.
- the parameter may be an amount of sunlight, an amount of current, an amount of humidity, and the like, and may be a vector including time information.
- the processor 232 may transmit a thermal image for each area collected in real time from the thermal image sensor 222 to the management server 300 through the communication unit 240. At this time, the processor 232 compares the thermal image for each region generated in real time with a temperature reference pattern for each region in which a pre-stored environmental factor is considered, and if the temperature increases compared to the reference pattern, the temperature for the region increases. Can be notified to the management server 300.
- the processor 232 immediately drives the fire extinguishing unit 270 to extinguish the fire when a spark occurs in a specific area or the temperature in a specific area rapidly rises above a preset temperature and a fire is expected, and the management server 300 Fire occurrence can be notified by.
- the communication unit 240 may receive a sensing value received from the sunlight amount sensor 110 and the sensor unit 120 in real time, and may perform data transmission/reception between the control unit 230 and the management server 300.
- the control circuit unit 250 may control driving of the switch 210, the heat pump 260, and the fire extinguishing unit 270 according to the control of the controller 230.
- the control unit 230 may control the driving of each component with the control circuit unit 250 according to the control signal received from the management server 300.
- control signal may be a signal for controlling off of a switch in which an abnormal current is detected, driving of a heat pump for humidity control, and the like.
- the heat pump 260 may prevent the occurrence of condensation in the connection panel 200.
- a heat pump 260 of an air heat source type is provided in the connection panel 200 to control cooling and heating inside the connection panel, thereby controlling humidity.
- the reference for cooling and heating control may be a reference humidity for preventing condensation.
- the control circuit unit 250 may control driving of the heat pump 260 by receiving a heat pump driving control signal for controlling the humidity inside the connection panel 200 to become the reference humidity from the analysis server 300. That is, the heat pump 260 is driven according to the control signal of the control circuit unit 250 to adjust the humidity inside the connection panel 200.
- connection panel 200 prevents condensation from occurring by a control signal that controls the packaging of the connection panel 200 using Gore-Tex and the bolt coupling structure and driving of the heat pump 260. Can be prevented.
- the management server 300 may include a data collection unit 310, a reference pattern generation unit 320, a correlation analysis unit 330, an abnormality prediction unit 340, and a monitoring unit 350. have.
- the data collection unit 310 may collect parameter sensing values transmitted from at least one connection panel 200 and store them in the DB 400. That is, change data for each amount of sunlight, amount of current, and amount of humidity collected in real time, and thermal image images for each region may be stored based on time. In this case, each of the pieces of information may be classified for each connection panel 200.
- the data collection unit 310 may collect information such as weather, temperature, humidity, rainfall, and amount of sunlight for each location of the solar cell 100 connected to the connection panel 200 from the meteorological office and store it in the DB 400.
- the reference pattern generation unit 320 may generate a model for each parameter, that is, a reference pattern, using data collected by the data collection unit 310 and stored in the DB 400.
- the reference pattern generation unit 320 generates a reference pattern for each connection panel 200, but considers environmental factors (solar cell installation location, shade, season, weather, etc.), and parameters for a preset period (for example, a day). You can create patterns. Accordingly, the reference pattern for each parameter of the amount of sunlight, current, and humidity is not a pattern having a fixed threshold, but may be generated in different models even at the same time according to environmental factors.
- the reference pattern generation unit 320 analyzes the thermal image for each region based on machine learning, but generates a temperature reference pattern for each region in which environmental factors of the connection panel are considered and transmits it to the connection panel.
- the reference pattern generation unit 320 may transmit and update the generated basic pattern to the connection panel 200 at a preset period.
- the correlation analysis unit 330 may generate a correlation model that analyzes the correlation between the analyzed basic pattern of sunlight amount and the basic pattern of the amount of current analyzed based on change data of the collected amount of sunlight based on the collected sunlight amount change data. .
- a correlation model may also be generated in consideration of environmental factors.
- FIG. 5 is a graph for explaining the correlation between the amount of sunlight and the amount of current reference pattern according to an embodiment of the present invention. Referring to FIG. 5, the amount of sunlight and the amount of electric current can be checked for a change over time. Through this, it is possible to grasp the correlation between the reference pattern of the amount of sunlight and the reference pattern of the amount of current according to the time trend.
- the abnormality prediction unit 340 predicts the current abnormality through analysis of the sunlight change data and current change data collected in real time, predicts the humidity abnormality through analysis of the humidity change data, and analyzes the thermal image collected in real time for each area.
- the temperature abnormality can be predicted through
- the abnormality prediction unit 340 analyzes the correlation between the measured amount of sunlight and the measured amount of current from the change data collected in real time, and determines the degree of similarity with the correlation model that analyzed the correlation between the amount of sunlight reference pattern and the current amount reference pattern. If is less than the preset rate, it can be judged as more than the current.
- the measured sunlight amount pattern may be a pattern generated by analyzing sunlight amount change data based on machine learning.
- the measured current amount pattern may be a pattern generated by analyzing current amount change data based on machine learning.
- the abnormality predictor 340 may determine a degree of similarity between the correlation between the measured sunlight amount pattern and the measured current amount pattern with the correlation between the sunlight amount reference pattern and the current amount reference pattern of FIG. 5. Referring to FIG. 6, when comparing the correlation between the reference pattern of the amount of sunlight and the reference pattern of the amount of current, the occurrence of an abnormality is predicted at a location where the correlation between the measured amount of sunlight pattern and the measured amount of current pattern is different, that is, a portion with low correlation similarity (abnormality prediction). Can be.
- the abnormality predicting unit 340 When determining a current abnormality, notifies the manager terminal (not shown), and transmits a control signal for turning off the switch of the corresponding solar cell module determined as the current abnormality to the connection panel 200, and By controlling 210, reverse current can be prevented.
- the abnormality prediction unit 340 is a heat pump for controlling the estimated humidity analyzed from the humidity change data collected in real time to become a pre-analyzed reference humidity by determining it as the abnormal humidity when the analyzed predicted humidity is outside the error range of the previously analyzed reference humidity
- the driving control signal may be transmitted to the connection panel 200.
- the monitoring unit 350 uses the monitoring unit 350 to monitor the heat of the corresponding area. Temperature patterns according to image images and abnormalities due to temperature rise can be notified to the manager terminal.
- the monitoring unit 350 visually provides a change trend predicted based on the change data collected in real time and a reference pattern, and may provide a mark and a notification sound that can be recognized when a notification occurs.
- connection panel 200 in the connection panel 200, the amount of sunlight, the amount of current, the humidity of the connection panel 200, and the thermal image for each area may be collected in real time in the connection panel 200 (S10). ).
- connection panel 200 may determine whether a change trend is predicted by comparing an interest section of each collected parameter with a pre-analyzed reference pattern (S15).
- abnormal prediction can be made according to the parameter.
- the current abnormality prediction analyzes the correlation between the measured amount of sunlight and the measured amount of current from the amount of sunlight change data and current change data collected in real time, and the degree of similarity with the correlation model that analyzes the correlation between the amount of sunlight reference pattern and the current amount reference pattern. By judging, if the degree of similarity is less than or equal to a preset rate, it can be determined as more than the current.
- the humidity abnormality prediction may be detected as abnormal humidity when the predicted humidity analyzed from the humidity change data collected in real time is out of the error range of the previously analyzed reference humidity.
- a control signal of the access panel 200 according to the abnormality prediction may be generated and transmitted to the access panel 200 (S35).
- the connection panel 200 receiving this may control the switch 210 and the heat pump 260 according to the control signal.
- the monitoring unit 350 when a thermal image abnormality is predicted, that is, when a notification by temperature rise is received from the thermal image of a specific area, the monitoring unit 350 enables the monitoring unit 350 to monitor the temperature in a temperature pattern according to the thermal image of the corresponding area. And an abnormality due to temperature rise may be notified to the manager terminal.
- the reference pattern may be updated at a preset period by parameters collected in real time, and the updated reference pattern may be transmitted to the access panel 200.
- FIGS. 1 to 6 what has been described with reference to FIGS. 1 to 6 above is a description of only the main matters of the present invention, and the present invention is limited to the configuration of FIGS. 1 to 6 as various designs are possible within the technical scope. It is self-evident that it is not.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Photovoltaic Devices (AREA)
Abstract
Description
Claims (16)
- 복수의 태양전지모듈을 포함하는 태양전지; 접속반; 및 상기 태양전지의 일조량, 상기 접속반의 전류 및 습도를 파라미터로 모니터링하는 관리서버;를 포함하고,A solar cell including a plurality of solar cell modules; Connection panel; And a management server for monitoring the amount of sunlight of the solar cell, current and humidity of the connection panel as parameters,상기 접속반은, The connection panel,상기 태양전지의 설치위치 및 환경요인을 고려하여 기분석된 파라미터별 기준패턴과 실시간 수집되는 파라미터와 비교하여 상기 파라미터의 변화추이를 예측하고, 예측된 변화추이로부터 추출된 예측 변곡점 및 변화추이 예측에 이용된 파라미터 정보를 변화데이터로 생성하며,In consideration of the installation location of the solar cell and environmental factors, by comparing the reference pattern for each parameter analyzed in advance with the parameter collected in real time, the change trend of the parameter is predicted, and the predicted inflection point and the change trend extracted from the predicted change trend are predicted. Generates the used parameter information as change data,상기 관리서버는,The management server,상기 접속반으로부터 파라미터별 변화데이터를 수신하고, 수신된 파라미터별 변화데이터를 머신러닝기반으로 분석한 파라미터별 기준패턴을 상기 접속반으로 전송하며, 상기 수신된 변화데이터로부터 이상감지시, 알림 및 상기 접속반으로 이상제어를 위한 제어신호를 제공하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.Receives parameter-specific change data from the access panel, transmits a parameter-specific reference pattern, which is analyzed based on machine learning, of the received parameter-specific change data to the access panel, and when an abnormality is detected from the received change data, a notification and the A machine learning-based solar power generation operation management system, characterized in that it provides a control signal for abnormality control to a connection panel.
- 제1항에 있어서,The method of claim 1,상기 접속반은, 파라미터별로 변화추이를 예측하되,The connection panel predicts the change trend for each parameter,실시간 수집되는 파라미터를 기설정된 관심구간 단위로 변화추이를 예측하고, 해당 관심구간에서 변화추이가 예측되는 경우에만 변화데이터를 생성하여 상기 관리서버로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.Machine learning-based photovoltaic power generation operation, characterized in that the parameters collected in real time are predicted in units of a preset interest section, and change data is generated and transmitted to the management server only when the change trend is predicted in the interest section. Management system.
- 제2항에 있어서,The method of claim 2,상기 관리서버는, The management server,일조량 기준패턴 및 전류량 기준패턴의 상관관계를 분석한 상관모델을 생성하고, 상기 실시간 수집되는 변화데이터로부터 실측 일조량 및 실측 전류량의 상관관계를 분석하여 상기 상관모델과의 유사도가 기설정률 이하이면 전류이상으로 판단하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.A correlation model that analyzes the correlation between the reference pattern of the amount of sunlight and the reference pattern of the amount of current is generated, and the correlation between the measured amount of sunlight and the measured amount of current is analyzed from the change data collected in real time. Machine learning-based solar power generation operation management system, characterized in that the above is determined.
- 제3항에 있어서,The method of claim 3,상기 관리서버는, The management server,상기 전류이상을 판단시, 관리자 단말로 알림하고, 전류이상으로 판단된 해당 태양전지모듈의 스위치를 오프시키는 제어신호를 상기 접속반으로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.A machine learning-based photovoltaic power generation operation management system, characterized in that when determining the current abnormality, a control signal for notifying a manager terminal and turning off a switch of a corresponding solar cell module determined as a current abnormality is transmitted to the connection panel.
- 제2항에 있어서,The method of claim 2,상기 접속반은 내부 습도 조절을 위한 히트펌프를 포함하고,The connection panel includes a heat pump for internal humidity control,상기 관리서버는, The management server,상기 실시간 수집되는 변화데이터로부터 분석된 예측습도가 기분석된 기준습도가 되도록 상기 히트펌프의 구동을 제어하는 제어신호를 상기 접속반으로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.A machine learning-based photovoltaic power generation operation management system, characterized in that transmitting a control signal for controlling driving of the heat pump to the connection panel so that the predicted humidity analyzed from the change data collected in real time becomes the pre-analyzed reference humidity.
- 제1항에 있어서,The method of claim 1,상기 접속반은,The connection panel,접속반 내부를 구분하여 영역별로 열화상 이미지를 생성하는 열화상 센서;A thermal image sensor that divides the interior of the connection panel and generates a thermal image for each area;실시간 생성되는 영역별 열화상 이미지를 상기 관리서버로 전송하되, 기저장된 환경요인이 고려된 영역별 온도 기준패턴과 비교시, 특정 영역에서 기준패턴 대비 온도가 상승하면 상기 관리서버로 알림하는 제어부를 포함하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.A control unit that transmits the thermal image for each region generated in real time to the management server, and notifies the management server when the temperature increases compared to the reference pattern in a specific region when comparing the temperature reference pattern for each region in which a pre-stored environmental factor is considered Machine learning-based photovoltaic operation management system comprising a.
- 제6항에 있어서,The method of claim 6,상기 접속반의 제어부는,The control unit of the connection panel,상기 생성된 열화상 이미지로 분석된 특정 영역에서의 온도가 급상승하여 화재가 예상되면 소화부를 구동시키고, 상기 관리서버로 화재발생을 알림하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.When a fire is expected due to a sudden increase in temperature in a specific area analyzed by the generated thermal image, the fire extinguishing unit is driven and the fire occurrence is notified to the management server.
- 제6항에 있어서,The method of claim 6,상기 관리서버는, The management server,상기 영역별 열화상 이미지를 머신러닝기반으로 분석하되, 환경요인이 고려된 영역별 온도 기준패턴을 생성하여 상기 접속반으로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리시스템.A machine learning-based photovoltaic power generation operation management system, characterized in that the thermal image for each area is analyzed based on machine learning, and a temperature reference pattern for each area in which environmental factors are considered is generated and transmitted to the connection panel.
- 복수의 태양전지모듈을 포함하는 태양전지; 접속반; 및 상기 태양전지의 일조량, 상기 접속반의 전류 및 습도를 파라미터로 모니터링하는 관리서버를 포함하는 시스템의 머신러닝기반 태양광발전운영관리방법에 있어서,A solar cell including a plurality of solar cell modules; Connection panel; And In the machine learning-based solar power generation operation management method of a system comprising a management server for monitoring the amount of sunlight of the solar cell, the current and humidity of the connection panel as parameters,상기 접속반에서, 상기 파리미터를 실시간 수집하는 단계;In the connection panel, collecting the parameters in real time;상기 접속반에서, 상기 태양전지의 설치위치 및 환경요인을 고려하여 기분석된 파라미터별 기준패턴과 상기 실시간 수집된 파라미터를 비교하여 상기 파라미터의 변화추이를 예측하는 단계;At the connection panel, predicting a change trend of the parameter by comparing a reference pattern for each parameter previously analyzed in consideration of the installation location and environmental factors of the solar cell and the parameters collected in real time;상기 접속반에서, 예측된 변화추이로부터 추출된 예측 변곡점 및 변화추이 예측에 이용된 파라미터 정보를 변화데이터로 생성하여 상기 관리서버로 전송하는 단계;Generating a predicted inflection point extracted from the predicted change trend and parameter information used for predicting the change trend as change data and transmitting it to the management server;상기 관리서버에서, 상기 변화데이터를 분석하여 이상예측을 감지하는 단계; 및Detecting an abnormal prediction by analyzing the change data in the management server; And상기 관리서버에서, 이상예측 감지시 상기 접속반으로 이상제어를 위한 제어신호를 제공하는 단계를 포함하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.And providing, at the management server, a control signal for abnormality control to the access panel upon detection of abnormality prediction.
- 제9항에 있어서,The method of claim 9,상기 변화추이를 예측하는 단계는,The step of predicting the change trend,실시간 수집되는 파라미터를 기설정된 관심구간 단위로 변화추이를 예측하되, 해당 관심구간에서 변화추이가 예측되는 경우에만 변화데이터를 생성하여 상기 관리서버로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.Machine learning-based photovoltaic power generation operation, characterized in that the parameters collected in real time are predicted in units of a preset interest section, but only when the change trend is predicted in the interest section, change data is generated and transmitted to the management server. Management method.
- 제10항에 있어서,The method of claim 10,상기 이상예측을 감지하는 단계는,The step of detecting the abnormal prediction,일조량 기준패턴 및 전류량 기준패턴의 상관관계를 분석한 상관모델을 생성하는 단계; 및Generating a correlation model by analyzing the correlation between the reference pattern of the amount of sunlight and the reference pattern of the amount of current; And상기 실시간 수집되는 변화데이터로부터 실측 일조량 및 실측 전류량의 상관관계를 분석하여 상기 상관모델과의 유사도가 기설정률 이하이면 전류이상으로 판단하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.A machine learning-based photovoltaic power generation operation management method, characterized in that the correlation between the measured amount of sunlight and the measured amount of current is analyzed from the change data collected in real time, and if the similarity with the correlation model is less than or equal to a preset rate, it is determined that the current is higher.
- 제11항에 있어서,The method of claim 11,상기 제어신호를 제공하는 단계는,Providing the control signal,상기 전류이상을 판단시, 관리자 단말로 알림하고, 전류이상으로 판단된 해당 태양전지모듈의 스위치를 오프시키는 제어신호를 상기 접속반으로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.When determining the current abnormality, the manager terminal is notified, and a control signal for turning off a switch of a corresponding solar cell module determined as a current abnormality is transmitted to the connection panel.
- 제10항에 있어서,The method of claim 10,상기 제어신호를 제공하는 단계는,Providing the control signal,상기 실시간 수집되는 변화데이터로부터 분석된 예측습도가 기분석된 기준습도가 되도록 상기 접속반에 구비된 히트펌프의 구동을 제어하는 제어신호를 상기 접속반으로 전송하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.Machine learning-based solar power, characterized in that the control signal for controlling driving of the heat pump provided in the connection panel is transmitted to the connection panel so that the predicted humidity analyzed from the change data collected in real time becomes the pre-analyzed reference humidity. Power generation operation management method.
- 제9항에 있어서,The method of claim 9,상기 접속반에서, 접속반 내부를 구분하여 영역별로 열화상 이미지를 실시간으로 생성하여 상기 관리서버로 전송하는 단계; 및 At the access panel, generating a thermal image for each area in real time by dividing the inside of the access panel and transmitting it to the management server; And기저장된 환경요인이 고려된 영역별 온도 기준패턴과 비교시, 특정 영역에서 기준패턴 대비 온도가 상승하면 상기 관리서버로 알림하는 단계를 더 포함하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.When comparing the temperature reference pattern for each region in which a pre-stored environmental factor is considered, the step of notifying the management server when the temperature increases compared to the reference pattern in a specific region. .
- 제14항에 있어서,The method of claim 14,상기 접속반에서, 상기 생성된 열화상 이미지로 분석된 특정 영역에서의 온도가 급상승하여 화재가 예상되면 소화부를 구동시키는 단계; 및In the connection panel, driving a fire extinguishing unit when a fire is expected due to a sudden increase in temperature in a specific area analyzed by the generated thermal image; And상기 관리서버로 화재발생을 알림하는 단계를 더 포함하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.Machine learning-based photovoltaic power generation operation management method further comprising the step of notifying the occurrence of fire to the management server.
- 제14항에 있어서,The method of claim 14,상기 관리서버에서, 환경요인을 적용하여 상기 실시간 수집된 일조량, 전류 및 습도를 분석한 일조량 기준패턴, 전류 기준패턴 및 습도 기준패턴을 생성하는 단계; Generating, in the management server, a sunlight amount reference pattern, a current reference pattern, and a humidity reference pattern by analyzing the amount of sunlight, current and humidity collected in real time by applying an environmental factor;상기 관리서버에서, 상기 영역별 열화상 이미지를 머신러닝기반으로 분석하되, 환경요인이 고려된 영역별 온도 기준패턴을 생성하는 단계; 및The management server, analyzing the thermal image for each area based on machine learning, and generating a temperature reference pattern for each area in which environmental factors are considered; And상기 접속반으로 파라미터별 기준패턴을 전송하는 단계를 더 포함하는 것을 특징으로 하는 머신러닝기반 태양광발전운영 관리방법.Machine learning-based photovoltaic operation management method, further comprising the step of transmitting a reference pattern for each parameter to the access panel.
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020190116795A KR102084784B1 (en) | 2019-09-23 | 2019-09-23 | Method for managing the operation of Photovoltaic Power Generation based on machine learning |
KR1020190116765A KR102084783B1 (en) | 2019-09-23 | 2019-09-23 | System for managing the operation of Photovoltaic Power Generation based on machine learning |
KR10-2019-0116795 | 2019-09-23 | ||
KR10-2019-0116765 | 2019-09-23 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021060772A1 true WO2021060772A1 (en) | 2021-04-01 |
Family
ID=75165062
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2020/012536 WO2021060772A1 (en) | 2019-09-23 | 2020-09-17 | Machine learning-based photovoltaic power generation operation management system and management method |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2021060772A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116131755A (en) * | 2023-02-23 | 2023-05-16 | 呼和浩特市语能科技有限责任公司 | Intelligent control system and method for solar power generation equipment |
CN116388685A (en) * | 2023-04-07 | 2023-07-04 | 江苏新之阳新能源科技有限公司 | Solar cell panel operation control system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101462247B1 (en) * | 2014-03-10 | 2014-11-21 | 삼성영상보안주식회사 | Smart fire detection system based on infrared thermal-image and interface platform for auto-fire extinguishing apparatus |
KR101761686B1 (en) * | 2017-03-31 | 2017-07-31 | (주)하모니앤유나이티드 | Real time predicting system for energy management system using machine learning |
KR101825725B1 (en) * | 2017-06-29 | 2018-02-06 | (주)위너스엔지니어링 | Method and device for diagnosing deterioration of solar cell module |
KR101922016B1 (en) * | 2018-07-19 | 2018-11-27 | 이우식 | Apparatus of photovoltaic power generation system with dew condensation prediction and preventional function |
KR20190007250A (en) * | 2017-07-12 | 2019-01-22 | (주)유에너지 | Moving type defect diagnosis system and diagnosis method for photovoltaic power generation equipment |
KR102084783B1 (en) * | 2019-09-23 | 2020-03-04 | 주식회사 아이팔 | System for managing the operation of Photovoltaic Power Generation based on machine learning |
KR102084784B1 (en) * | 2019-09-23 | 2020-05-26 | 주식회사 아이팔 | Method for managing the operation of Photovoltaic Power Generation based on machine learning |
-
2020
- 2020-09-17 WO PCT/KR2020/012536 patent/WO2021060772A1/en active Application Filing
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101462247B1 (en) * | 2014-03-10 | 2014-11-21 | 삼성영상보안주식회사 | Smart fire detection system based on infrared thermal-image and interface platform for auto-fire extinguishing apparatus |
KR101761686B1 (en) * | 2017-03-31 | 2017-07-31 | (주)하모니앤유나이티드 | Real time predicting system for energy management system using machine learning |
KR101825725B1 (en) * | 2017-06-29 | 2018-02-06 | (주)위너스엔지니어링 | Method and device for diagnosing deterioration of solar cell module |
KR20190007250A (en) * | 2017-07-12 | 2019-01-22 | (주)유에너지 | Moving type defect diagnosis system and diagnosis method for photovoltaic power generation equipment |
KR101922016B1 (en) * | 2018-07-19 | 2018-11-27 | 이우식 | Apparatus of photovoltaic power generation system with dew condensation prediction and preventional function |
KR102084783B1 (en) * | 2019-09-23 | 2020-03-04 | 주식회사 아이팔 | System for managing the operation of Photovoltaic Power Generation based on machine learning |
KR102084784B1 (en) * | 2019-09-23 | 2020-05-26 | 주식회사 아이팔 | Method for managing the operation of Photovoltaic Power Generation based on machine learning |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116131755A (en) * | 2023-02-23 | 2023-05-16 | 呼和浩特市语能科技有限责任公司 | Intelligent control system and method for solar power generation equipment |
CN116131755B (en) * | 2023-02-23 | 2024-04-26 | 青岛中筑新能源有限公司 | Intelligent control system and method for solar power generation equipment |
CN116388685A (en) * | 2023-04-07 | 2023-07-04 | 江苏新之阳新能源科技有限公司 | Solar cell panel operation control system |
CN116388685B (en) * | 2023-04-07 | 2024-04-09 | 江苏新之阳新能源科技有限公司 | Solar cell panel operation control system |
CN116388685B8 (en) * | 2023-04-07 | 2024-04-26 | 青岛中筑新能源有限公司 | Solar cell panel operation control system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021060772A1 (en) | Machine learning-based photovoltaic power generation operation management system and management method | |
WO2019103230A1 (en) | Solar light power generation management system | |
KR102084784B1 (en) | Method for managing the operation of Photovoltaic Power Generation based on machine learning | |
US6653549B2 (en) | Photovoltaic power generation systems and methods of controlling photovoltaic power generation systems | |
WO2021066259A1 (en) | System and method for analyzing data of photovoltaic power plant | |
KR102262547B1 (en) | Accident Management System of Solar Combiner Box | |
KR102084783B1 (en) | System for managing the operation of Photovoltaic Power Generation based on machine learning | |
WO2019059525A1 (en) | Photovoltaic lighting system having integrated control board, and monitoring system using same | |
WO2021221249A1 (en) | Smart livestock management system and method for same | |
WO2021045576A1 (en) | Battery protection apparatus and method using gas sensor | |
KR102054613B1 (en) | Fire monitoring system and method for solar power connector | |
WO2023003356A1 (en) | Gantry crane real-time monitoring system | |
WO2022085833A1 (en) | System for diagnosing degradation of photovoltaic generation | |
WO2018155848A1 (en) | Electrical fire prevention system of solar power generation facility | |
WO2021201369A1 (en) | Fire outbreak prediction system and method therefor | |
WO2018043875A1 (en) | Photovoltaic generation device having fire prevention function and breakdown diagnosis function | |
WO2018199659A1 (en) | Method for asset management of substation | |
WO2019190049A1 (en) | System for managing circuit breaker in distribution switchboard | |
WO2018056503A1 (en) | System and method for switching line short-circuit fault section in inverter-based stand-alone microgrid | |
WO2020013619A1 (en) | Substation asset management method and apparatus based on power system reliability index | |
WO2024071607A1 (en) | Smart platform for explosion-proof inspection in industrial site | |
WO2018199656A1 (en) | Method for asset management of substation | |
WO2017099335A1 (en) | Method and system for maintaining wind power facility on basis of weather information | |
WO2015170904A1 (en) | Remote diagnostic system and method for photovoltaic module | |
WO2022102812A1 (en) | Ess fire prevention system and method therefor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20868408 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20868408 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12.09.2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20868408 Country of ref document: EP Kind code of ref document: A1 |