KR102084783B1 - System for managing the operation of Photovoltaic Power Generation based on machine learning - Google Patents

Abstract

The present invention relates to a photovoltaic power generation operating and management system based on machine learning and, more specifically, to a photovoltaic power generation operating and management system based on machine learning, comprising: a solar cell; a connection board comparing a solar cell parameter collected in real time with a pre-analyzed reference pattern in consideration of the installation locations and environmental factors of the solar cell to predict a change trend of the parameter, and generating information on the parameter used for predicting the change trend and a predicted inflection point extracted from the predicted change trend as change data; and a management server receiving the change data of each parameter from the connection board and transmitting a reference pattern for each parameter, obtained by analyzing the received change data of each parameter through machine learning to the connection board, and providing an alarm when abnormality is detected from the received change data and providing a control signal for abnormality control to the connection board.

Description

System for managing the operation of Photovoltaic Power Generation based on machine learning}

The present invention relates to a machine learning based photovoltaic operation management system.

More specifically, the change of the parameter is predicted by comparing the previously analyzed reference pattern with the parameters of the solar cell collected in real time in consideration of the solar cell, the installation location of the solar cell and environmental factors, and extracted from the predicted change. The reference panel for each parameter that receives the change data for each parameter from the access panel for generating the predicted inflection point and the parameter information used for the change trend prediction as change data, and analyzes the received change data for each parameter on the basis of machine learning. The machine learning based photovoltaic operation management system comprising a management server which transmits to the access panel and provides notification when an abnormality is detected from the received change data and a control signal for abnormal control to the access panel. It is about.

Recently, due to the excessive use of fossil fuels, environmental problems such as global warming have become serious, and it is urgent to prepare measures to reduce carbon dioxide emissions internationally, and as an alternative, interest in renewable energy is increasing.

In addition, green energy sources, including solar cells, have the advantage of not using fossil fuels that are limited to the earth, and there is no carbon dioxide gas emission, which minimizes environmental pollution. These advantages include global warming and fossil fuels. Considering the position of the modern man who has to prepare for the near future, which is becoming increasingly depleted, its importance is very high.

In Korea, in order to regulate CO2 emissions, incentive policies for the supply of new and renewable energy have been institutionalized and implemented, with the leading of photovoltaic power generation. As the power generation system is recommended, numerous power generation facilities and infrastructure facilities for its operation have been developed and thousands of MW photovoltaic power generation facilities are currently in operation.

These solar modules are installed directly on the roof of a building where a lot of solar radiation can be obtained, or in a secluded place such as Yasan where sunshine can be secured, so the operator's access is usually not easy and the power generation system is installed. It is not realistic to check with the naked eye at the site. Thus, the importance of automatic fault recognition for remote monitoring and power generation systems has increased.

Korean Patent No. 10-0999978 measures a plurality of solar cell modules for converting solar energy into electrical energy and outputting the inverter, an inverter for converting power output from the plurality of solar cell modules, and measures generated voltage and current. In addition, the photovoltaic monitoring control device that monitors and controls the abnormality of overvoltage, overcurrent and reverse current in the circuit group to which each solar cell module is connected, and the switching unit which cuts the power according to the monitoring result and the information thereof is received. It is characterized by consisting of a data collection and monitoring device for collecting and monitoring data.

However, the photovoltaic-related technology according to the prior art has been developed focusing only on the individual performance and specific parameter improvement of each module constituting the photovoltaic facility. Therefore, there is a need for technology development to improve the overall operational efficiency of the photovoltaic power generation facilities.

Accordingly, the present applicant provides a machine learning based photovoltaic operation management system that predicts the change of parameters collected in real time using the reference pattern analyzed based on machine learning, and controls the access panel when detecting abnormality through the predicted change. I would like to.

1. Korean Registered Patent No. 10-0999978 (announced Dec. 2010)

An object of the present invention, the machine learning based photovoltaic power generation operation for predicting the change in the parameters collected in real time using the reference pattern analyzed on the basis of machine learning, and control the access panel during abnormal detection through the predicted change To provide a management system.

Machine learning-based photovoltaic power generation operation management system according to an embodiment of the present invention for achieving the above object includes a solar cell, a connection panel and the amount of sunshine of the solar cell, the connection panel including a plurality of solar cell modules It includes a management server for monitoring the current and humidity as parameters,

The access panel predicts the change trend of the parameter by comparing the parameter of the parameter and the collected parameters in real time, considering the installation location and environmental factors of the solar cell, and predicting inflection points extracted from the predicted change trend. And parameter information used for the change trend prediction may be the change data.

In addition, the management server receives the change data for each parameter from the access panel, and transmits the parameter reference pattern for each parameter analyzed based on the machine learning based on the received change data for each parameter to the access panel, from the received change data When an abnormality is detected, a notification and a control signal for abnormality control may be provided to the access panel.

In addition, the access panel predicts the change trend for each parameter, but predicts the change trend in units of a predetermined interest section in real time, and generates the change data only when the change trend is predicted in the corresponding interest section. You can send it to the server.

The management server may generate a correlation model that analyzes the correlation between the sunshine reference pattern and the current reference pattern, and analyzes the correlation between the measured sunshine amount and the measured current amount from the change data collected in real time to obtain a similarity with the correlation model. If is less than the preset rate can be determined as more than the current.

The management server may notify the manager terminal of the current abnormality and transmit a control signal to the access panel to switch off the solar cell module determined to be the current abnormality.

In addition, the access panel includes a heat pump for adjusting the internal humidity, and the management server, the control to control the driving of the heat pump so that the predicted humidity analyzed from the real-time collected change data is analyzed based on the reference humidity A signal can be sent to the access panel.

In addition, the access panel, a thermal image sensor for generating a thermal image for each region by dividing the inside of the access panel, and transmits the thermal image for each region generated in real time to the management server, but for each region considering the pre-stored environmental factors In comparison with the temperature reference pattern, a control unit may notify the management server when the temperature rises in the specific region compared to the reference pattern.

The controller of the access panel may drive a fire extinguishing unit when a fire is expected due to a sudden rise in temperature in a specific region analyzed by the generated thermal image, and may notify the management server of the fire.

The management server may analyze the thermal image for each region on a machine learning basis, and generate a temperature reference pattern for each region in consideration of environmental factors of the access panel and transmit it to the access panel.

As described above, the machine learning based photovoltaic operation management system of the present invention is based on the big data analyzed reference pattern in consideration of the installation location and environmental factors (time, season, shadow, weather, etc.) of the solar cell, It can predict the change trend of collected parameters in real time and detect abnormality.

In addition, it is possible to improve the accuracy of the change trend even when the environment changes by transmitting the relevant information to the management server only when predicting the change trend of the parameters collected in real time, and analyzing the big data.

In addition, when an abnormality of the parameter is detected, a notification may be provided to the manager terminal, and the driving of the access panel may be controlled using a control signal. In particular, when the fire is predicted due to a sudden rise in temperature and sparkle, the fire extinguishing unit is immediately operated in the connection panel to prevent a large damage due to the fire, and to prevent the occurrence of reverse current by turning off the switch in which the current abnormality is detected.

In addition, it can be monitored by visualizing and providing parameter information according to the change trend and abnormality detection of parameters collected in real time.

1 is a block diagram showing a schematic configuration of a machine learning based photovoltaic operation management system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a configuration of the controller of FIG. 1.
3 is a graph illustrating a parameter change trend prediction according to an embodiment of the present invention.
4 is a block diagram showing the configuration of the management server of FIG.
5 is a graph illustrating the correlation between the amount of sunshine and the change amount of current reference pattern according to an embodiment of the present invention.
FIG. 6 is a graph illustrating an abnormality of a sunshine amount and a current amount change pattern collected in real time according to an exemplary embodiment.
7 is a flowchart illustrating a machine learning based photovoltaic operation management method according to an embodiment of the present invention.

The terms or words used in this specification and claims are not to be construed as limiting in their usual or dictionary meanings, and the inventors may appropriately define the concepts of terms in order to best describe their invention. It should be interpreted as meanings and concepts corresponding to the technical idea of the present invention based on the principle that the present invention.

Therefore, the embodiments described in the specification and the configuration shown in the drawings are only the most preferred embodiments of the present invention and do not represent all of the technical idea of the present invention, various equivalents that may be substituted for them at the time of the present application It should be understood that there may be water and variations.

Before describing the present invention with reference to the drawings, it is not shown or specifically described for the matters that are not necessary to reveal the gist of the present invention, that is, can be obviously added to those skilled in the art. Make a note.

1 is a block diagram showing a schematic configuration of a machine learning based photovoltaic operation management system according to an embodiment of the present invention. Machine learning-based photovoltaic power generation operation management system according to an embodiment of the present invention (hereinafter referred to as a system) is a solar cell 100, the sun light sensor 110, access panel 200, management server 300 and DB 400 may be included.

The system of the present invention provides a visual monitoring and monitoring of the amount of sunshine, the amount of current, the humidity and temperature of the connection panel 200 during the photovoltaic power generation operation, the manager terminal when the risk factors are predicted during monitoring (Not shown).

At this time, the system of the present invention can predict the change trend by comparing the parameters collected in real time with the reference pattern analyzed based on big data machine learning, and update the reference pattern periodically based on this to accurately predict the change trend.

The solar cell 100 converts light energy incident from the sun into electrical energy and outputs the electrical energy. The solar cell 100 includes a plurality of solar cell arrays (100a to 100n). In addition, the solar cell array includes a plurality of solar cell modules. A plurality of solar cell modules that are components of each solar cell array are configured in series with each other.

The sunshine sensor 110 is installed on the panel of the solar cell 100, and senses the amount of sunshine at the location where the solar cell 100 is installed in real time, and controls the amount of sunshine being sensed through the communication unit 240 of the connection panel 200. And transmit to 230.

The connection panel 200 compares the sunshine amount received from the sunshine sensor 110 in real time, the output current received from the solar cell 100, the humidity and the temperature in the connection panel 200 with corresponding reference patterns, and compares the change trend for each parameter. It can be predicted.

Referring to FIG. 1, 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. In addition, the connection panel 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 housing is coupled. Accordingly, when differential pressure is generated due to temperature change, the external panel (for example, rain, etc.) is formed by equilibrating pressure inside and outside the connection panel 200 by packaging and coupling bolts of the connection panel 200 using Gore-Tex. Prevents penetration and prevents condensation.

The switch 210 may receive the output power of the solar cell 100 in units of strings. In this case, the control circuit unit 250 may merge the output power of the string unit received under the control of the controller 230 and provide it to the inverter.

The current sensor 222 may sense the current of each string unit from the output power received in the string unit of the solar cell 100 and provide the current to the controller 230.

The humidity sensor 222 may sense the humidity in the connection panel 300 in real time and provide the same to the controller 230.

The thermal image sensor 223 may provide the controller 230 with a thermal image obtained by photographing a thermal image in the connection panel 300 in real time. In this case, the thermal image may be obtained by dividing a plurality of areas in the connection panel 300 into respective areas. In this case, the control circuit unit 250 having a high heat generation temperature may be concentrated.

In detail, the thermal image sensor 220 may obtain a real-time thermal image by dividing an area of the control circuit unit 250 by a circuit configuration or by dividing it into a unit area by an area position of the control circuit unit 250. In this case, the thermal image generated in real time may be transmitted to the controller 230.

Referring to FIG. 2, the controller 230 may include a memory 231 and a processor 232.

The memory 231 may receive a sensing value for each parameter sensed by each of the sensors 110 and 220. That is, the memory 231 may store the amount of sunshine, the amount of current for each string, the amount of humidity, and the thermal image for each region, and may store the reference pattern for each parameter updated from the management server 300 at a preset cycle.

Here, the reference pattern for each parameter is a pattern in which the management server 300 analyzes the change amount of each parameter on the basis of big data machine learning, and the environmental location such as the installation location (place, shadow, etc.) of the solar cell, weather, season, time, etc. The factor can be analyzed in consideration of the factors.

At this time, the installation location of the solar cell can be divided into a plurality of places installed in the region and the area, the system of the present invention can monitor by analyzing and managing the parameters by location and region of each location. On the other hand, the analysis of the reference pattern for each parameter to be described in detail in the description of the management server (300).

The processor 232 may predict the change trend of the real-time parameter sensing value by comparing the parameter-specific sensing value stored in the memory 231 with the reference pattern of the corresponding parameter. 3, the parameter change trend prediction of the processor 232 will be described.

3 is a graph for explaining parameter change trend prediction according to an embodiment of the present invention. Referring to FIG. 3, the processor 232 may compare a pattern of parameters collected in real time (actually) with a reference pattern previously stored in the memory 231. In this case, the pattern of the measured parameter and the reference pattern may represent the degree of change of the sensing value of the parameter sensing value over time.

In this case, the processor 232 samples a sensing value of a parameter collected in real time in a predetermined time interval unit, sets an interval of interest (sampled unit interval) for predicting a sensing value trend, and detects the sensing values of parameters in the interval of interest. The trend of the sensing value may be predicted based on the current time t1 by comparing the pattern values in the corresponding interest intervals of the reference pattern.

In this case, the sensing value trend prediction may use a short-term load forecasting (STLF) analysis technique. The processor 232 may extract the predicted inflection point P from the predicted sensing value trend pattern through the STLF analysis.

When extracting the predicted inflection point P, the processor 232 generates meta data including an amount of change in a sensing value and a predicted inflection point P in the interval of interest used to predict the predicted inflection point P as the change data and the management server 300. ) Can be sent. That is, the relevant information may be transmitted to the management server 300 only when the change of the parameter according to the reference pattern is predicted.

In this case, the parameter may be the amount of sunshine, the amount of current, the amount of humidity, and the like, and may be a vector including time information.

On the other hand, the processor 232 may transmit the thermal image for each region 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 generated for each region in real time with the temperature reference pattern for each region in consideration of pre-stored environmental factors, and if the temperature increases compared to the reference pattern, the temperature rise for the region is present. The management server 300 can be notified.

In addition, when a spark is expected in a specific region or a temperature in a specific region rises above a predetermined temperature and a fire is expected, the processor 232 immediately drives the fire extinguishing unit 270 to extinguish the fire, and the management server 300 It can notify the fire occurrence.

The communication unit 240 may receive the sensing values received from the sunshine sensor 110 and the sensor unit 120 in real time, and may transmit and receive data between the control unit 230 and the management server 300.

The control circuit 250 may control the driving of the switch 210, the heat pump 260, and the fire extinguishing unit 270 under the control of the controller 230. In this case, the controller 230 may control the driving of each component by the control circuit 250 according to the control signal received from the management server 300.

For example, the control signal may be a signal for controlling the off of the switch in which the abnormal current is sensed, the driving of the heat pump for humidity control, and the like.

The heat pump 260 may prevent the occurrence of condensation in the connection panel 200. The control panel 200 is provided with an air heat source type heat pump 260 to control humidity of the heating and cooling inside the connection panel. At this time, the reference during the heating and cooling control may be a reference humidity for preventing condensation.

The control circuit unit 250 may control the driving of the heat pump 260 by receiving a heat pump driving control signal for controlling the humidity inside the connection panel 200 to be the reference humidity from the analysis server 300. That is, the heat pump 260 may be driven according to the control signal of the control circuit 250 to adjust the humidity inside the connection panel 200.

Accordingly, the connection panel 200 according to an embodiment of the present invention generates condensation by a control signal for controlling the packaging and bolt coupling structure of the connection panel 200 using the Gore-Tex and the driving of the heat pump 260. It can prevent.

4 is a block diagram showing the configuration of the management server of FIG. Referring to FIG. 4, the management server 300 may include a data collector 310, a reference pattern generator 320, a correlation analyzer 330, an abnormality predictor 340, and a monitor 350. have.

The data collector 310 may collect parameter sensing values transmitted from the at least one access panel 200 and store the parameter sensing values in the DB 400. That is, the change data for each of the amount of sunshine, the amount of current and the amount of humidity collected in real time and the thermal image for each region may be stored based on time. In this case, each piece of information may be divided by the access panel 200.

In addition, the data collection unit 310 may collect information such as weather, temperature, humidity, rainfall, amount of sunshine, etc. of each location of the solar cell 100 connected to the access panel 200 from the Meteorological Agency and store it in the DB 400.

The reference pattern generator 320 may generate a model, that is, a reference pattern, for each parameter by using the data collected by the data collector 310 and stored in the DB 400.

The reference pattern generator 320 generates a reference pattern for each access panel 200, but takes into account parameters during a preset period (eg, one day) in consideration of environmental factors (solar cell installation location, shadow, season, weather, etc.). You can create a pattern. Thus, the reference pattern for the parameters of the amount of sunshine, current and humidity may be generated by different models even at the same time according to environmental factors, not a pattern having a fixed threshold.

In addition, the reference pattern generator 320 may analyze the thermal image for each region on a machine learning basis, and generate a temperature reference pattern for each region in consideration of the connection environment factors and transmit the generated region to the access panel.

The reference pattern generator 320 may update the generated basic pattern by transmitting the generated basic pattern to the access panel 200 at a preset period.

The correlation analyzer 330 may generate a correlation model that analyzes the correlation between the basic amount of sunshine analyzed based on the collected change data of sunshine and the basic current pattern analyzed based on the collected change data of current amount. . In this case, a correlation model may also be generated in consideration of environmental factors.

5 is a graph illustrating a correlation between the amount of sunshine and the amount of current reference pattern according to an embodiment of the present invention. Referring to FIG. 5, the amount of sunshine and the amount of current can be seen as the amount of change over time. Through this, the correlation between the sunshine reference pattern and the current reference pattern can be identified.

The abnormality predicting unit 340 predicts a current abnormality through analysis of the collected sunlight change data and the current change data in real time, predicts an abnormality of humidity through the analysis of humidity change data, and analyzes the thermal image collected in real time for each region. You can predict the temperature abnormality through.

Specifically, the abnormality predicting unit 340 analyzes the correlation between the actual amount of sunlight and the amount of current measured from the change data collected in real time, and determines the similarity with the correlation model that analyzes the correlation between the amount of sunlight reference pattern and the amount of current reference pattern. If is less than the preset rate can be determined as more than the current.

FIG. 6 is a graph illustrating an abnormality in the amount of sunshine and a current variation pattern collected in real time according to an exemplary embodiment. Referring to FIG. 6, the measured sunshine amount pattern may be a pattern generated by analyzing sunshine amount change data on a machine learning basis. In addition, the measured current amount pattern may be a pattern generated by analyzing the current amount change data on a machine learning basis.

The abnormality predicting unit 340 may determine the 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 compared with the correlation between the sunshine reference pattern and the current reference pattern, abnormality is predicted at a position where the correlation between the measured sunshine amount pattern and the measured current amount pattern is different, that is, a portion having low correlation similarity (abnormal prediction). Can be.

The abnormality predicting unit 340 notifies the manager terminal (not shown) when the current abnormality is determined, and transmits a control signal to the access panel 200 to turn off the switch of the solar cell module determined to be the current abnormality to the corresponding switch. By controlling the 210, reverse current can be prevented.

In addition, the abnormality predicting unit 340 is a heat pump for controlling the predicted humidity analyzed from the humidity change data collected in real time out of the error range of the previously analyzed standard humidity, so as to determine the abnormal humidity to the previously analyzed reference humidity. The driving control signal may be transmitted to the connection panel 200.

In addition, when the abnormality predicting unit 340 receives a notification due to the temperature increase from the thermal image of the specific region from the access panel 200, the abnormality predicting unit 340 may monitor the corresponding region in order to intensively monitor the corresponding region. The abnormality according to the temperature pattern and the temperature rise according to the image image may be notified to the manager terminal.

The monitoring unit 350 may visually provide a change trend predicted based on the collected change data and the reference pattern in real time, and may provide a mark and a notification sound that can be recognized when an alert occurs.

7 is a flowchart illustrating a machine learning based photovoltaic operation management method according to an embodiment of the present invention. Referring to FIGS. 1 to 6, in the access panel 200, the amount of sunshine, the amount of current, the humidity of the access panel 200, and the thermal image for each region may be collected in real time (S10). ).

Next, in the access panel 200, it is possible to determine whether the change trend is predicted by comparing the interval of interest of each collected parameter with the previously analyzed reference pattern (S15).

At this time, if the change trend is predicted (S20: Y), metadata including the parameter indices collected during the interval of interest used for the change trend prediction and the predicted inflection point P predicted by the change trend is generated as change data (S20: Y). S25) can be transmitted to the management server (300).

Next, the management server 300, by receiving the change data can predict the abnormality (S30). At this time, abnormal prediction may be performed according to a parameter.

Specifically, the current anomaly prediction analyzes the correlation between the amount of sunshine and the amount of current measured from the amount of sunshine change data and the current change data collected in real time, and compares the similarity with the correlation model that analyzes the correlation between the sunshine reference pattern and the current reference pattern. By judging, if the similarity is equal to or less than the preset rate, it may be determined that the current is higher.

In addition, the humidity abnormality prediction may be detected as the 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 standard humidity.

Next, when the abnormal prediction is notified to the manager terminal, it is possible to generate a control signal to the access panel 200 according to the abnormal prediction can be transmitted to the access panel 200 (S35). In the connection panel 200 receiving this, the switch 210 and the heat pump 260 may be controlled according to a control signal.

In addition, visualized information may be provided to monitor real-time parameters and reference patterns. That is, it can be monitored by visualizing and providing parameter information according to the change trend and abnormality detection of parameters collected in real time.

In particular, when a thermal image abnormality is predicted, that is, when a notification of a temperature rise is received from a thermal image of a specific region, the monitoring unit 350 monitors the temperature in accordance with the thermal image of the region so that the region can be monitored. And the abnormality of the temperature rise can be notified to the manager terminal.

On the other hand, the reference pattern may be updated at a predetermined period by the parameters collected in real time, the updated reference pattern may be transmitted to the access panel 200.

In addition, what was described above using FIG. 1 thru | or 6 described only the main matter of this invention, and this invention is limited to the structure of FIG. 1 thru | or 6 as many designs are possible within the technical scope. It is not clear.

100: solar cell 100a ~ 100n: solar cell module
110: sunshine sensor 200: connection panel
210: switch 220: sensor
221: current sensor 222: humidity sensor
223: thermal image sensor 230: control unit (MCU)
231: memory 232: processor
240: communication unit 250: control circuit unit
260 heat pump 270 fire extinguishing
300: management server 400: DB
310: data collection unit 320: reference pattern generation unit
330: correlation analysis unit 340: abnormal prediction unit
350: monitoring unit

Claims (8)

A solar cell including a plurality of solar cell modules; Connection board; And a management server that monitors the amount of sunshine of the solar cell, the current and humidity of the connection panel as parameters.
The connecting panel,
In consideration of the installation position and environmental factors of the solar cell, and compared with the standard analysis parameters and the parameters collected in real time to predict the change trend of the parameter, and to predict the predicted inflection point and change trend extracted from the predicted change trend Generates the used parameter information as change data,
The management server,
Receives the change data for each parameter from the access panel, and transmits the reference pattern for each parameter, which is analyzed based on the machine learning based on the received change data for each parameter to the access panel, when detecting abnormality from the received change data, notification and the Provides a control signal for abnormal control to the connection panel,
The management server,
Generating a correlation model analyzing the correlation between the sunshine reference pattern and the current reference reference pattern, and analyzing the correlation between the measured sunshine amount and the measured current amount from the change data collected in real time, and if the similarity with the correlation model is equal to or less than a preset rate, the current Judging by the above,
The connecting panel,
Machine learning-based photovoltaic power generation operation management system characterized in that it is packaged with functional fibers to prevent the penetration of rain into the connection panel and prevent the occurrence of condensation inside the connection panel.
The method of claim 1,
The access panel predicts a change trend for each parameter,
Machine learning based photovoltaic power generation operation characterized by predicting the change trend in units of a predetermined interest section in real time collected parameters, and generating the change data and transmitting it to the management server only when the change trend is predicted in the corresponding interest section. Management system.
delete The method of claim 1,
The management server,
When the current abnormality is determined, notifying the manager terminal, and transmits a control signal for switching off the corresponding solar cell module determined to be the current abnormality to the access panel to the machine learning based solar power generation operation management system.
The method of claim 2,
The connection panel includes a heat pump for adjusting the internal humidity,
The management server,
And a control signal for controlling driving of the heat pump to the access panel so that the predicted humidity analyzed from the real-time collected change data is previously analyzed.
The method of claim 1,
The connecting panel,
A thermal image sensor for generating a thermal image for each region by dividing the inside of the access panel;
The control unit transmits a thermal image of each region generated in real time to the management server, but notifies the management server when the temperature is increased compared to the reference pattern in a specific area when compared with the temperature reference pattern for each area in consideration of pre-stored environmental factors. Machine learning based photovoltaic power generation operation management system comprising a.
The method of claim 6,
The control unit of the connection panel,
Machine running based photovoltaic power generation operation management system, characterized in that to drive the fire extinguisher if the temperature is expected to rise in a specific region analyzed by the thermal image generated by the fire, and to notify the fire to the management server.
The method of claim 6,
The management server,
Machine thermal analysis of each area based on the machine learning, the machine learning based photovoltaic power generation operation management system, characterized in that for generating a reference temperature pattern for each area in consideration of environmental factors and transmitting to the access panel.

Images