JP7812249B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Patent Document 1 discloses a method for predicting the amount of power generated by a solar power generation system by region and weather, which uses the global solar radiation intensity calculated from atmospheric transmittance, direct solar radiation intensity, and diffuse solar radiation intensity, the solar cell operating temperature calculated from the global solar radiation intensity and the regional daily minimum temperature measured by a weather station, the solar cell operating temperature power generation amount calculated from the solar cell operating temperature, the DC power generation amount calculated from the operating temperature power generation amount, and the AC power generation amount calculated from the DC power generation amount to predict the amount of power generation at any time interval.

Patent Document 2 discloses a method for predicting the power generation amount of a solar power generation system using a solar power generation system prediction device, the method comprising: a solar radiation prediction formula deriving means for deriving a solar radiation prediction formula based on weather phenomena previously observed in the area where the solar power generation system is installed and solar radiation previously measured in the area; a solar radiation prediction calculation means for predicting the solar radiation amount in the area by inputting a weather forecast for the area on a target prediction day or time period and solar radiation measured in the area before the prediction time on the target prediction day into the solar radiation prediction formula; and a power generation prediction calculation means for predicting the power generation amount of the solar power generation system by inputting the predicted solar radiation and a temperature forecast for the area on a target prediction day or time period into a solar power generation system model capable of calculating the power generation amount from solar radiation and temperature information.

Japanese Patent Application Publication No. 10-108486 Japanese Patent Application Laid-Open No. 2006-33908

If it were possible to predict failures in solar power generation equipment, it would be possible to prevent failures by replacing solar panels or taking other measures before a failure occurs. However, it has traditionally been difficult to accurately predict failures in solar power generation equipment.

Therefore, the present invention aims to provide an information processing device, information processing method, and information processing program that can accurately predict failures in solar power generation equipment.

The information processing device of the first aspect includes a reference data acquisition unit that acquires reference data including power generation data relating to the past power generation amount of a solar power generation device that receives sunlight and generates electricity, and weather forecast data relating to weather forecasts for the area where the solar power generation device is installed; a power generation prediction unit that predicts the power generation amount of the solar power generation device based on the reference data acquired by the reference data acquisition unit; an actual power generation amount acquisition unit that acquires the actual power generation amount of the solar power generation device corresponding to the power generation amount predicted in the past by the power generation amount prediction unit; and a failure prediction unit that predicts a failure of the solar power generation device based on the difference between the power generation amount predicted in the past by the power generation amount prediction unit and the actual power generation amount acquired by the actual power generation amount acquisition unit.

The information processing device of the second aspect is the information processing device of the first aspect, wherein the reference data acquisition unit further acquires power loss data related to power loss of the photovoltaic power generation device.

The information processing device of the third aspect is the information processing device of the first or second aspect, and includes a verification unit that verifies whether the amount of power generation predicted by the power generation amount prediction unit needs to be corrected, and a correction unit that corrects the predicted amount of power generation when the verification unit determines that the amount of power generation needs to be corrected.

A fourth aspect of the information processing device is the third aspect of the information processing device, in which the correction unit corrects the predicted amount of power generation based on the immediately preceding amount of power generation.

In a fifth aspect of the information processing method, a computer acquires reference data including power generation data relating to the past power generation amount of a photovoltaic power generation device that receives sunlight and generates electricity, and weather forecast data relating to weather forecasts for the area where the photovoltaic power generation device is installed, predicts the power generation amount of the photovoltaic power generation device based on the acquired reference data, acquires the actual power generation amount of the photovoltaic power generation device corresponding to the previously predicted power generation amount, and executes a process of predicting a failure of the photovoltaic power generation device based on the difference between the previously predicted power generation amount and the acquired actual power generation amount.

The information processing program of the sixth aspect causes a computer to acquire reference data including power generation data relating to the past power generation amount of a photovoltaic power generation device that receives sunlight and generates electricity, and weather forecast data relating to weather forecasts for the area where the photovoltaic power generation device is installed, predict the power generation amount of the photovoltaic power generation device based on the acquired reference data, acquire the actual power generation amount of the photovoltaic power generation device corresponding to the previously predicted power generation amount, and execute a process of predicting a failure of the photovoltaic power generation device based on the difference between the previously predicted power generation amount and the acquired actual power generation amount.

This invention makes it possible to accurately predict failures in solar power generation equipment.

1 is a diagram showing a schematic configuration of an information processing system according to an embodiment of the present invention; 2 is a block diagram showing the hardware configuration of an information processing device and a power plant terminal according to the present embodiment. FIG. FIG. 2 is a block diagram showing the configuration of a storage unit of the information processing device according to the present embodiment. 1 is a block diagram illustrating an example of a functional configuration of an information processing device according to an embodiment of the present invention. 10 is a flowchart showing the flow of a failure prediction process performed by the information processing device according to the present embodiment.

The information processing system 10 according to this embodiment will be described below.

The information processing system 10 according to this embodiment is a system for predicting failures in photovoltaic power generation equipment.

In this embodiment, the solar power generation equipment is a low-voltage grid-connected power generation facility, but is not limited to this. In other words, the solar power generation equipment may be a low-voltage grid-connected power generation facility with a power plant capacity of less than 50 kW, or a high-voltage grid-connected power generation facility with a power plant capacity of 50 kW or more.

Figure 1 shows the general configuration of the information processing system 10.

As shown in FIG. 1, the information processing system 10 includes an information processing device 20 and multiple power plant terminals 30. Each power plant terminal 30 is connected to a solar power generation device 40. The multiple power plant terminals 30 and solar power generation devices 40 are installed in different regions.

The information processing device 20 and multiple power plant terminals 30 are connected via a network N and can communicate with each other.

The information processing device 20 is a server computer owned by a specified business operator. The information processing device 20 predicts the amount of power generated by the solar power generation device 40 based on reference data including power generation data relating to the past amount of power generated by the solar power generation device 40, which generates electricity from sunlight, and weather forecast data relating to weather forecasts for the area where the solar power generation device 40 is installed, and predicts a failure of the solar power generation device 40 based on the difference between the amount of power generated in the past and the actual amount of power generated by the solar power generation device 40 corresponding to the predicted amount of power generation.

The power plant terminal 30 is a terminal owned by the power plant where the solar power generation equipment 40 is installed. The power plant terminal 30 transmits power generation amount data and power loss data of the solar power generation equipment 40 to the information processing device 20.

Next, the hardware configuration of the information processing device 20 and the power plant terminal 30 will be explained. Figure 2 is a block diagram showing the hardware configuration of the information processing device 20 and the power plant terminal 30. Note that since the information processing device 20 and the power plant terminal 30 basically have a general computer configuration, the information processing device 20 will be explained as a representative.

As shown in FIG. 2, the information processing device 20 includes a CPU 21 (Central Processing Unit), a ROM 22 (Read Only Memory), a RAM 23 (Random Access Memory), a storage unit 24, an input unit 25, a display unit 26, and a communication unit 27. Each component is connected to each other via a bus 28 so that they can communicate with each other.

The CPU 21 is a central processing unit that executes various programs and controls each component. That is, the CPU 21 reads programs from the ROM 22 or the storage unit 24 and executes the programs using the RAM 23 as a work area. The CPU 21 controls the above components and performs various calculations in accordance with the programs stored in the ROM 22 or the storage unit 24.

ROM 22 stores various programs and data. RAM 23 serves as a working area for temporarily storing programs or data.

The memory unit 24 is composed of a storage device such as a hard disk drive (HDD), solid state drive (SSD), or flash memory, and stores various programs and data.

The input unit 25 includes a pointing device such as a mouse, a keyboard, a microphone, a camera, etc., and is used to perform various inputs.

The display unit 26 is, for example, a liquid crystal display, and displays various information. The display unit 26 may also function as the input unit 25 by adopting a touch panel system.

The communication unit 27 is an interface for communicating with other devices. For this communication, for example, a wired communication standard such as Ethernet (registered trademark) or FDDI, or a wireless communication standard such as 4G, 5G, or Wi-Fi (registered trademark) is used.

Figure 3 is a block diagram showing the configuration of the memory unit 24 of the information processing device 20.

As shown in FIG. 3, the storage unit 24 stores an information processing program 24A for causing the CPU 21 of the information processing device 20 to function as the functional configuration shown in FIG. 4, which will be described later. When executing the information processing program 24A, the information processing device 20 uses the hardware resources shown in FIG. 2 to perform processing based on the information processing program 24A.

Next, we will explain the functional configuration of the information processing device 20.

Figure 4 is a block diagram showing an example of the functional configuration of the information processing device 20.

As shown in FIG. 4, the CPU 21 of the information processing device 20 has, as its functional components, a reference data acquisition unit 21A, a power generation amount prediction unit 21B, a performance power generation amount acquisition unit 21C, a failure prediction unit 21D, a verification unit 21E, and a correction unit 21F. Each functional component is realized by the CPU 21 reading and executing the information processing program 24A stored in the memory unit 24.

The reference data acquisition unit 21A acquires reference data including power generation amount data relating to the past power generation amount of the solar power generation device 40, which receives sunlight and generates electricity, and weather forecast data relating to the weather forecast for the area where the solar power generation device 40 is installed. The reference data acquired by the reference data acquisition unit 21A is stored in the memory unit 24.

In addition, in this embodiment, the reference data acquisition unit 21A further acquires power loss data related to the power loss of the solar power generation device 40.

Past power generation data is acquired, for example, from the power plant terminal 30 of the power plant where a failure is to be predicted. When requested by the information processing device 20, the power plant terminal 30 transmits past power generation data of the photovoltaic power generation equipment 40, for example, power generation data from the past 10 to 30 years, to the information processing device 20.

The weather forecast data is information about the weather forecast for the area where the solar power generation equipment 40 is installed, and includes weather forecasts, weather advisories, and weather warnings. The weather forecast data is obtained, for example, from an external device (not shown). The external device transmits weather forecast data corresponding to the area where the solar power generation equipment 40 is installed to the information processing device 20.

The power loss data is acquired, for example, from the power plant terminal 30 of the power plant where a failure is to be predicted. The power loss data is data indicating the degree of power loss that will occur in the power generation of the photovoltaic power generation equipment 40. The power loss varies depending on the season, weather conditions in each region, and the like. The power loss also varies depending on conditions specific to the photovoltaic power generation equipment 40, such as loss in the cable connecting the solar panel and the power conditioner. For this reason, the power loss data includes monthly power loss data, yearly power loss data, and power loss specific to the installation environment of the photovoltaic power generation equipment 40.

When requested by the information processing device 20, the power plant terminal 30 transmits power loss data of the solar power generation equipment 40 to the information processing device 20.

The power generation amount prediction unit 21B predicts the amount of power generated by the photovoltaic power generation device 40 based on the reference data acquired by the reference data acquisition unit 21A. That is, the power generation amount prediction unit 21B predicts the amount of power generated by the photovoltaic power generation device 40 at a specified prediction time based on past power generation amount data, weather forecast data, and power loss data acquired by the reference data acquisition unit 21A. The prediction time may be, for example, on a daily or monthly basis from the next day onwards, or may be on a time basis such as 30 minutes or 1 hour in the future.

Specifically, for example, when past power generation data, weather forecast data, power loss data, and the predicted time are input, a trained model that is trained through machine learning to output the predicted power generation amount at the predicted time is used to predict the power generation amount. The learning model can be trained using, for example, well-known supervised learning.

The actual power generation amount acquisition unit 21C acquires the actual power generation amount of the photovoltaic power generation device 40 corresponding to the power generation amount previously predicted by the power generation amount prediction unit 21B. Specifically, the actual power generation amount acquisition unit 21C acquires, from the past power generation amount data acquired by the reference data acquisition unit 21A, the past power generation amount for a period that coincides with the prediction period of the power generation amount previously predicted by the power generation amount prediction unit 21B as the actual power generation amount.

The failure prediction unit 21D predicts a failure of the photovoltaic power generation device 40 based on the difference between the amount of power generation previously predicted by the power generation amount prediction unit 21B and the amount of actual power generation acquired by the actual power generation amount acquisition unit 21C. That is, if the difference between the amount of power generation previously predicted by the power generation amount prediction unit 21B and the amount of actual power generation acquired by the actual power generation amount acquisition unit 21C is equal to or greater than a predetermined threshold, it predicts that there is a possibility that the photovoltaic power generation device 40 will fail. On the other hand, if the difference between the amount of power generation previously predicted by the power generation amount prediction unit 21B and the amount of actual power generation acquired by the actual power generation amount acquisition unit 21C is less than the predetermined threshold, it predicts that there is no possibility that the photovoltaic power generation device 40 will fail. The threshold is set in advance, for example, based on the actual failure history of the photovoltaic power generation device 40.

The verification unit 21E verifies whether the amount of power generation predicted by the power generation amount prediction unit 21B needs to be revised. For example, if the amount of power generation predicted by the power generation amount prediction unit 21B satisfies a predetermined revision condition, the verification unit 21E determines that the predicted amount of power generation needs to be revised. On the other hand, if the amount of power generation predicted by the power generation amount prediction unit 21B does not satisfy the predetermined revision condition, the verification unit 21E determines that the predicted amount of power generation does not need to be revised. For example, if there is a continuous period of sunny weather, the change in the amount of power generation is likely to be small, so revision of the predicted amount of power generation may be unnecessary. Conversely, if the weather is alternating between cloudy and sunny weather, the change in the amount of power generation is likely to be large, so revision of the predicted amount of power generation may be necessary. Therefore, for example, a revision condition may be set such that the predicted amount of power generation needs to be revised if there is not a predetermined consecutive period of sunny weather, and the predicted amount of power generation does not need to be revised if there is a predetermined consecutive period of sunny weather.

The correction unit 21F corrects the predicted power generation amount based on the most recent power generation amount. Specifically, the correction unit 21F obtains the most recent power generation amount, for example the most recent power generation amount, of the photovoltaic power generation device 40 for which a failure is to be predicted from the power plant terminal 30. Then, when the most recent power generation amount and the predicted power generation amount are input, the correction unit 21F corrects the power generation amount using a trained model trained by machine learning to output a corrected predicted power generation amount. The learning model can be trained, for example, using known supervised learning.

Figure 5 is a flowchart showing the flow of failure prediction processing as information processing performed by the information processing device 20. The CPU 21 reads the information processing program 24A from the storage unit 24, expands it into the RAM 23, and executes it to perform failure prediction processing.

In step S100 shown in FIG. 5, the CPU 21 acquires power generation data relating to the past power generation amount of the photovoltaic power generation device 40. That is, the CPU 21 requests the power plant terminal 30 of the power plant where the photovoltaic power generation device 40 for which a failure is to be predicted is installed to transmit power generation data relating to the past power generation amount, and acquires the power generation data relating to the past power generation amount from the power plant terminal 30.

In step S101, the CPU 21 acquires weather forecast data relating to the weather forecast for the region where the photovoltaic power generation equipment 40 is installed. That is, the CPU 21 requests the external device to transmit weather forecast data for the region where the power plant where a failure is to be predicted is installed, and acquires the weather forecast data from the external device.

In step S102, the CPU 21 acquires power loss data. That is, it requests the power plant terminal 30 of the power plant where the solar power generation device 40 for which a failure is to be predicted is installed to send the power loss data, and acquires the power loss data from the power plant terminal 30. The power loss data is acquired from the power plant terminal 30 of the power plant for which a failure is to be predicted.

In step S103, the CPU 21 predicts the amount of power generated by the photovoltaic power generation device 40 at a specified prediction time based on the past power generation data acquired in step S100, the weather forecast data acquired in step S101, and the power loss data acquired in step S102. That is, the past power generation data, weather forecast data, power loss data, and prediction time are input into the trained model, and the predicted power generation amount at the prediction time is obtained.

In step S104, the CPU 21 verifies whether the amount of power generation predicted in step S103 needs to be corrected. That is, it determines whether the predicted amount of power generation satisfies predetermined correction conditions. If the amount of power generation predicted in step S103 satisfies the correction conditions, it determines that correction is necessary, and proceeds to step S105. On the other hand, if the amount of power generation predicted in step S103 does not satisfy the correction conditions and it is determined that correction is not necessary, it proceeds to step S106.

In step S105, the amount of power generation predicted in step S103 is corrected. That is, for example, the most recent amount of power generation is obtained from the power plant terminal 30, and the obtained most recent amount of power generation and the amount of power generation predicted in step S103 are input into the trained model, and the corrected amount of power generation is obtained.

In step S106, the CPU 21 acquires the actual power generation amount of the photovoltaic power generation device 40 corresponding to the power generation amount previously predicted in step S103. That is, from the past power generation amount data acquired in step S100, the past power generation amount for the period that coincides with the prediction period of the previously predicted power generation amount is acquired as the actual power generation amount.

In step S107, the CPU 21 predicts a failure of the photovoltaic power generation device 40 based on the difference between the amount of power generation previously predicted in step S103 and the actual amount of power generation acquired in step S105. That is, if the difference between the amount of power generation previously predicted in step S103 and the actual amount of power generation acquired in step S105 is equal to or greater than a predetermined threshold, it predicts that there is a possibility of a failure of the photovoltaic power generation device 40. On the other hand, if the difference between the amount of power generation previously predicted in step S103 and the actual amount of power generation acquired in step S105 is less than the predetermined threshold, it predicts that there is no possibility of a failure of the photovoltaic power generation device 40. In this way, if there is a large discrepancy between the predicted amount of power generation and the actual amount of power generation, it is determined that a malfunction has occurred in the photovoltaic power generation device 40, the amount of power generation commensurate with the prediction will not be obtained, and there is a possibility of a failure.

In step S108, the CPU 21 determines whether or not it predicted in step S107 that there is a possibility of failure of the photovoltaic power generation device 40. If it predicted in step S107 that there is a possibility of failure of the photovoltaic power generation device 40, it proceeds to step S109. On the other hand, if it predicted in step S107 that there is no possibility of failure of the photovoltaic power generation device 40, it terminates this routine.

In step S109, the power plant terminal 30 is notified that the solar power generation equipment 40 may malfunction. This can prompt the user to replace the solar panels of the solar power generation equipment 40, etc.

As described above, the information processing device 20 is a server computer owned by a specified business operator. The information processing device 20 predicts the amount of power generated by the solar power generation device 40 based on reference data including power generation amount data relating to the past amount of power generated by the solar power generation device 40, which generates electricity from sunlight, weather forecast data relating to weather forecasts for the area where the solar power generation device 40 is installed, and power loss data, and predicts a failure of the solar power generation device 40 based on the difference between the amount of power generated in the past and the actual amount of power generated by the solar power generation device 40 corresponding to the predicted amount of power generation.

In this embodiment, the case where power loss data is also used to predict power generation amount has been described, but power generation amount may also be predicted without using power loss data. In other words, the processing of step S102 in Figure 5 may be omitted.

Furthermore, in this embodiment, we have described a case where it is verified whether the predicted power generation amount needs to be corrected, and if a correction is necessary, the predicted power generation amount is corrected. However, the predicted power generation amount may also be used as is. In other words, the processing of steps S104 and S105 in Figure 5 may be omitted.

In the above embodiment, the information processing performed by the CPU 21 by loading software (programs) may be performed by various processors other than a CPU. Examples of processors in this case include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays), whose circuit configuration can be changed after manufacture, and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations designed specifically to perform specific processes. Information processing may be performed by one of these various processors, or by a combination of two or more processors of the same or different types (e.g., multiple FPGAs, or a combination of a CPU and an FPGA). The hardware structure of these various processors is, more specifically, an electrical circuit that combines circuit elements such as semiconductor devices.

In the above embodiment, the information processing program 24A is pre-stored (installed) in the storage unit 24, but this is not limiting. The information processing program 24A may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The information processing program 24A may also be downloaded from an external device via the network N.

REFERENCE SIGNS LIST 10 Information processing system 20 Information processing device 21A Reference data acquisition unit 21B Power generation amount prediction unit 21C Actual power generation amount acquisition unit 21D Failure prediction unit 21E Verification unit 21F Correction unit 24 Storage unit 24A Information processing program 30 Power plant terminal 40 Photovoltaic power generation equipment

Claims (5)

a reference data acquisition unit that acquires reference data including power generation amount data relating to past power generation amounts of a solar power generation device that generates electricity by receiving sunlight, weather forecast data relating to weather forecasts for the area where the solar power generation device is installed, and power loss data that is data indicating the amount of power loss that occurs in the power generation of the solar power generation device;
a power generation amount prediction unit that predicts the amount of power generated by the photovoltaic power generation device at a predetermined future prediction time based on the reference data acquired by the reference data acquisition unit;
an actual power generation amount acquisition unit that acquires an actual power generation amount of the photovoltaic power generation device corresponding to the power generation amount predicted in the past by the power generation amount prediction unit;
a failure prediction unit that predicts a failure of the photovoltaic power generation device based on a difference between the power generation amount predicted in the past by the power generation amount prediction unit and the actual power generation amount acquired by the actual power generation amount acquisition unit;
a verification unit that determines that the amount of power generation predicted by the power generation amount prediction unit needs to be corrected when a period of clear weather has not continued for a predetermined period, and that the amount of power generation predicted by the power generation amount prediction unit at the predetermined future prediction time does not need to be corrected when a period of clear weather has continued for a predetermined period;
a correction unit that corrects the power generation amount predicted in the past by the power generation amount prediction unit when the verification unit determines that the power generation amount at the predetermined future prediction time needs to be corrected;
An information processing device comprising: The information processing apparatus according to claim 1 , wherein the power loss data includes monthly power loss data, annual power loss data, and power loss data specific to the installation environment. The information processing device according to claim 1 , wherein the correction unit corrects the amount of power generation predicted in the past by the power generation amount prediction unit based on the latest actual amount of power generation acquired by the actual amount of power generation acquisition unit . The computer
acquire reference data including power generation amount data relating to the past power generation amount of a solar power generation device that generates electricity by receiving sunlight, weather forecast data relating to the weather forecast for the area where the solar power generation device is installed, and power loss data which is data indicating the amount of power loss that occurs in the power generation of the solar power generation device;
predicting the amount of power generated by the photovoltaic power generation device at a predetermined future prediction time based on the acquired reference data;
Acquire the actual power generation amount of the photovoltaic power generation device corresponding to the power generation amount predicted in the past;
predicting a failure of the photovoltaic power generation device based on a difference between the predicted power generation amount in the past and the acquired actual power generation amount ;
If the period of sunny weather is not consecutive for a predetermined period, it is determined that the predicted amount of power generation needs to be corrected, and if the period of sunny weather is consecutive for a predetermined period, it is determined that the predicted amount of power generation at the predetermined future prediction time does not need to be corrected;
When it is determined that the amount of power generation at the predetermined future prediction time needs to be corrected, the amount of power generation predicted in the past is corrected.
An information processing method that performs processing. On the computer,
acquire reference data including power generation amount data relating to the past power generation amount of a solar power generation device that generates electricity by receiving sunlight, weather forecast data relating to the weather forecast for the area where the solar power generation device is installed, and power loss data which is data indicating the amount of power loss that occurs in the power generation of the solar power generation device;
predicting the amount of power generated by the photovoltaic power generation device at a predetermined future prediction time based on the acquired reference data;
Acquire the actual power generation amount of the photovoltaic power generation device corresponding to the power generation amount predicted in the past;
predicting a failure of the photovoltaic power generation device based on a difference between the predicted power generation amount in the past and the acquired actual power generation amount ;
If the period of sunny weather is not consecutive for a predetermined period, it is determined that the predicted amount of power generation needs to be corrected, and if the period of sunny weather is consecutive for a predetermined period, it is determined that the predicted amount of power generation at the predetermined future prediction time does not need to be corrected;
When it is determined that the amount of power generation at the predetermined future prediction time needs to be corrected, the amount of power generation predicted in the past is corrected.
An information processing program that executes processing.