Photovoltaic power generation forecasting system, photovoltaic power generation forecasting method, photovoltaic power generation forecasting program, past forecast estimation device, past forecast estimation method, and past forecast estimation program

Abstract

To enable precise prediction of a photovoltaic power generation amount to be started in a relatively short time when predicting the photovoltaic power generation amount using a learning device that receives weather forecast data as input data.SOLUTION: In a past forecast estimation unit 22, past weather forecast history data is estimated and generated in a learning device that receives past weather actual history data as input data. Herein, the past weather actual history data is weather actual history data at a plurality of time points in the past, and the past weather forecast history data is weather forecast history data at the plurality of time points in the past. A machine learning processing unit 26 performs machine learning of the learning device in a photovoltaic power generation amount prediction unit 25 using the past weather forecast history data generated by the past forecast estimation unit 22.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a photovoltaic power generation amount prediction system, a photovoltaic power generation amount prediction method, a photovoltaic power generation amount prediction program, a past forecast estimation device, a past forecast estimation method, and a past forecast estimation program. [Background technology]

[0002] One power generation prediction system uses a neural network to predict future solar power generation based on past meteorological measurement data and future meteorological forecast data for a certain point in time (see, for example, Patent Document 1).

[0003] Furthermore, one solar power generation amount prediction system captures sky images with a camera and predicts future solar power generation amount based on the sky images (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2018-007312 [Patent Document 2] Japanese Patent Application Laid-Open No. 2017-200360 Summary of the Invention [Problem to be solved by the invention]

[0005] In the above-mentioned power generation prediction system, future weather forecast data at each point in time is used as input data for the neural network, so weather forecast data at many points in time over a long period of time is required as learning data when machine learning the neural network.

[0006] However, while past measured weather data is relatively easy to obtain, it is difficult to obtain past weather forecast data. Weather forecast data providers are reluctant to provide past weather forecast data because it would reveal the accuracy of their weather forecasts. Therefore, it is difficult to perform appropriate machine learning until weather forecast data has been collected over a long period of time. In other words, it is difficult to start accurately predicting solar power generation in a relatively short period of time. While it is possible to use measured weather data instead of weather forecast data, in this case, the tendency of values ​​taken by the forecast data and the measured data differs, which may result in inaccurate machine learning.

[0007] The present invention has been made in consideration of the above-mentioned problems, and aims to provide a solar power generation prediction system, a solar power generation prediction method, and a solar power generation prediction program that can start to accurately predict solar power generation in a relatively short time when predicting solar power generation using a learning device that uses weather forecast data as input data, as well as a past forecast estimation device, a past forecast estimation method, and a past forecast estimation program that can be used for the machine learning. [Means for solving the problem]

[0008] The solar power generation prediction system of the present invention includes a solar power generation prediction unit that predicts solar power generation using a first learning device that uses weather forecast data as input data, a past forecast estimation unit that estimates and generates past weather forecast history data from past actual weather history data, and a first machine learning processing unit that performs machine learning on the first learning device using the past weather forecast history data generated by the past forecast estimation unit.

[0009] The solar power generation prediction method of the present invention includes a solar power generation prediction step of predicting solar power generation using a first learning device that uses weather forecast data as input data, a past forecast estimation step of estimating and generating past weather forecast history data from past actual weather history data, and a machine learning processing step of performing machine learning on the first learning device using the past weather forecast history data generated in the past forecast estimation step.

[0010] The solar power generation prediction program of the present invention causes a computer to execute a solar power generation prediction step of predicting solar power generation using a first learning device that uses weather forecast data as input data, a past forecast estimation step of estimating and generating past weather forecast history data from past actual weather history data, and a machine learning processing step of performing machine learning on the first learning device using the past weather forecast history data generated in the past forecast estimation step.

[0011] The past forecast estimation device according to the present invention includes a past forecast estimation unit that estimates and generates past weather forecast history data using a learning device that receives past actual weather history data as input data. Here, the past actual weather history data is actual weather history data from multiple points in time in the past, and the past weather forecast history data is weather forecast history data from multiple points in time in the past.

[0012] The past forecast estimation method according to the present invention includes a past forecast estimation step of estimating and generating past weather forecast history data using a learning device that receives past actual weather history data as input data, where the past actual weather history data is actual weather history data at multiple points in time in the past, and the past weather forecast history data is weather forecast history data at multiple points in time in the past.

[0013] The past forecast estimation program according to the present invention causes a computer to execute a past forecast estimation step of estimating and generating past weather forecast history data using a learning device that receives past actual weather history data as input data, where the past actual weather history data is actual weather history data from multiple points in time in the past, and the past weather forecast history data is weather forecast history data from multiple points in time in the past. [Effects of the Invention]

[0014] According to the present invention, there are provided a solar power generation prediction system, a solar power generation prediction method, and a solar power generation prediction program that can perform appropriate machine learning in a relatively short time when predicting solar power generation using a learning device that uses weather forecast data as input data, as well as a past forecast estimation device, a past forecast estimation method, and a past forecast estimation program that can be used for the machine learning.

[0015] The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings. [Brief explanation of the drawings]

[0016] [Figure 1] FIG. 1 is a block diagram showing the configuration of a solar power generation amount prediction system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing the configuration of the past forecast estimation unit 22 in the solar power generation amount prediction system shown in FIG. [Figure 3] FIG. 3 is a block diagram showing the configuration of the solar power generation amount prediction unit 25 in the solar power generation amount prediction system shown in FIG. [Figure 4] FIG. 4 is a block diagram showing the configuration of the solar radiation amount predicting unit 41 in the solar power generation amount predicting unit 25 shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0017] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0018] Fig. 1 is a block diagram showing the configuration of a solar power generation prediction system according to an embodiment of the present invention. The solar power generation prediction system shown in Fig. 1 is configured with one information processing device (such as a personal computer), but processing units and other units described below may be distributed among multiple information processing devices that are capable of data communication with each other. Furthermore, such multiple information processing devices may include a GPU (Graphics Processing Unit) that processes specific calculations in parallel.

[0019] The photovoltaic power generation prediction system shown in FIG. 1 is a system for predicting the amount of power generated by, for example, a specific photovoltaic power generation facility, and includes a storage device 1, a communication device 2, a user interface 3, and a processing device 4.

[0020] The storage device 1 is a non-volatile storage device such as a flash memory or a hard disk, and stores various data and programs.

[0021] Here, the storage device 1 stores a past forecast estimation program 11 and a solar power generation prediction program 12, and also stores a parameter dataset 13 (parameters such as the neural network coupling coefficients (weights) and biases described below) as needed.

[0022] The communication device 2 is a device capable of data communication, such as a network interface, a peripheral device interface, or a modem, and performs data communication with other devices as necessary.

[0023] The user interface 3 includes a display device 3a such as a display that displays an operation screen and the like, and an input device 3b such as a keyboard that accepts user operations.

[0024] In FIG. 1, the user interface 3 is connected to the arithmetic processing unit 4 via an internal bus or a peripheral device interface. Alternatively, for example, if the arithmetic processing unit 4 is built into a server on a network (such as the Internet or a LAN (Local Area Network)), the user interface 3 serves as a user interface device for a terminal device that can communicate with the server, and functions as a user interface for processing units and units realized in the arithmetic processing unit 4 through data communication between the server and the terminal device.

[0025] The arithmetic processing device 4 is a computer equipped with a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), etc., and operates as various processing units by loading programs from the ROM, storage device 1, etc. into the RAM and executing them on the CPU. The RAM is used as a work memory for the processing units.

[0026] Here, by executing the program 11, the arithmetic processing device 4 operates as a past actual data acquiring unit 21, a past forecast estimating unit 22, and a machine learning processing unit .

[0027] The past actual data acquisition unit 21 acquires actual measurement data for specific items (temperature, humidity, solar radiation, cloud area ratio, etc.) in past weather forecasts. For example, the past actual data acquisition unit 21 downloads actual measurement data from a specific server using the communication device 2, or reads actual measurement data stored in advance in the storage device 1.

[0028] The past forecast estimation unit 22 estimates and generates past weather forecast history data using a learning device that receives past actual weather history data as input data. Here, this past actual weather history data is actual weather history data from multiple points in time in the past, and this past weather forecast history data is weather forecast history data from the multiple points in time in the past.

[0029] In this embodiment, the past forecast estimation unit 22 estimates and generates past weather forecast history data using a learning device, using past actual weather history data, cloud area ratio history data, and solar position history data as input data.

[0030] The learning device is machine-learned using past actual weather history data and past weather forecast history data of a specific weather forecast provider as learning data, and the past forecast estimation unit 22 estimates and generates past weather forecast history data for a specific weather forecast provider. In other words, for each of multiple weather forecast providers, past weather forecast history data (values ​​of each item of weather forecast for multiple future time points viewed from a past time point) specific to that weather forecast provider is individually generated.

[0031] FIG. 2 is a block diagram showing the configuration of the past forecast estimation unit 22 in the solar power generation amount prediction system shown in FIG.

[0032] For example, as shown in FIG. 2, the past forecast estimation unit 22 includes an encoder 31, encoders 32-1 to 32-3, a feature vector connection unit 33, a latent space encoder , and a decoder .

[0033] The encoder 31 includes a neural network with one or more layers (here, a fully connected neural network), and converts the above-mentioned actual weather history data (input data) into a feature vector using the neural network.

[0034] The encoder 32-1 has one or more layers of neural networks (here, a fully connected neural network) that convert cloud area ratio history data (input data) into feature vectors. The encoder 32-2 has one or more layers of neural networks (here, a fully connected neural network) that convert time history data (input data) into feature vectors. The encoder 32-3 has one or more layers of neural networks (here, a fully connected neural network) that convert sun position history data (input data) into feature vectors.

[0035] The input data of the neural networks in the encoders 31, 32-1 to 32-3, etc. is properly normalized (for example, to a range of 0 to 1). Furthermore, periodic input data (sun position and time) is normalized using a sine function or a cosine function.

[0036] The actual meteorological measurements (temperature, humidity, wind direction, wind speed, etc.), cloud area ratio values, and solar position values ​​(elevation angle and azimuth angle) at each point in time are identified, and the actual meteorological measurements for multiple points in time are treated as historical meteorological data, the cloud area ratio values ​​for those multiple points in time are treated as cloud area ratio data, and the solar position values ​​for those multiple points in time are treated as historical solar position data.

[0037] The feature vector concatenation unit 33 concatenates the feature vectors generated by the encoders 31, 32-1 to 32-3 into one feature vector.

[0038] The latent space encoder 34 includes a neural network, and uses the neural network to map the concatenated feature vectors obtained by the feature vector concatenation unit 33 in the latent space.

[0039] The decoder 35 includes a neural network, which converts the feature vectors mapped by the latent space encoder 34 into weather forecast prediction history data (output data).

[0040] The machine learning processing unit 23 performs machine learning of the learning unit (here, the above-mentioned neural network) in the past forecast estimation unit 22 using an existing learning method (such as backpropagation). Specifically, the machine learning processing unit 23 updates the parameters of the learning unit (here, the weights and biases of the neural network) using learning data including multiple sets of pairs of input data and output data of the learning unit.

[0041] Once a certain period of input data has been obtained and machine learning by the learning device (here, the above-mentioned neural network) in the past forecast estimation unit 22 has been completed, the past forecast estimation unit 22 will be able to estimate past forecast values ​​for weather forecast items (temperature, humidity, wind direction, wind speed, etc.) from past measured values, making it possible to obtain a large number of past forecast values ​​in a relatively short period of time, and these forecast values ​​will be used for machine learning in the machine learning processing unit 26 described below.

[0042] Here, by executing the program 12, the arithmetic processing device 4 operates as an input data acquisition unit 24, a solar power generation amount prediction unit 25, and a machine learning processing unit .

[0043] The input data acquisition unit 24 acquires input data for the solar power generation facility for which the solar power generation amount is to be predicted. The input data includes, for example, sky image history data, actual weather history data, power generation condition history data, satellite forecast data, weather forecast data, and cloud area ratio history data. For example, the input data acquisition unit 24 downloads the input data from a specific server using the communication device 2 or reads the input data stored in advance in the storage device 1.

[0044] The solar power generation amount prediction unit 25 predicts the solar power generation amount using a learning device that uses weather forecast data as input data.

[0045] In this embodiment, the solar power generation prediction unit 25 predicts the solar power generation amount using a learning device that receives weather forecast data (forecast values ​​for each item of weather forecast for multiple future points in time from the present time) and sky image history data as multimodal input data, and this learning device (a) generates solar radiation prediction data from the sky image history data, and (b) generates a predicted value of the solar power generation amount from the solar radiation prediction data and the weather forecast data. Note that the sky image history data is image data of a series of sky images obtained by photographing the sky at multiple points in time with an imaging device from the power generation facility that is the target for predicting the solar power generation amount.

[0046] Fig. 3 is a block diagram showing the configuration of a solar power generation amount prediction unit 25 in the solar power generation amount prediction system shown in Fig. 1. Fig. 4 is a block diagram showing the configuration of an insolation amount prediction unit 41 in the solar power generation amount prediction unit 25 shown in Fig. 3.

[0047] For example, as shown in FIG. 3, the solar power generation amount predicting unit 25 includes an insolation amount predicting unit 41, encoders 42-1 to 42-4, a data linking unit 43, and a power generation amount predicting unit 44.

[0048] The solar radiation prediction unit 41 includes a learning device that derives predicted solar radiation values ​​for multiple future points in time from input data such as sky image history data, weather forecast data, cloud area ratio forecast data, and time data. The solar radiation prediction unit 41 is common to all solar power generation facilities (i.e., it has been machine-learned to be common to multiple solar power generation facilities). However, encoders 51 and 52 (described below) in the solar radiation prediction unit 41 are specific to the solar power generation facility and differ for each solar power generation facility (i.e., it has been machine-learned to be different for each solar power generation facility).

[0049] The sky image history data, weather forecast data, cloud area ratio forecast data, and time data are data indicating sky images, weather forecasts, cloud area ratio forecasts, and times at multiple points in time up to the present. These sky images are generated by scaling and cropping the captured images so that they have a predetermined number of pixels. The weather forecasts, cloud area ratio forecasts, and times are normalized as appropriate.

[0050] As shown in FIG. 4, the solar radiation amount prediction unit 41 includes an encoder 51, an encoder 52, a feature vector connection unit 53, and a solar radiation amount prediction value calculation unit .

[0051] The encoder 51 includes a convolutional neural network (CNN) that converts the blank image history data into a feature vector. The CNN of the encoder 51 includes a long short-term memory (LSTM) layer and a global average pooling (GAP) layer.

[0052] The encoder 52 has a neural network including an LSTM layer, and uses weather forecast data (wind speed, wind direction, etc. at specific times), cloud area ratio forecast data (forecasted values ​​of cloud area ratio at those specific times), and solar position data (elevation angle and azimuth angle at those specific times) as input data, and converts the input data into a feature vector.

[0053] The feature vector concatenation unit 53 concatenates the feature vectors generated by the encoders 51 and 52 into one feature vector.

[0054] The solar radiation predicted value calculation unit 54 includes a neural network with one or more layers (here, a fully connected neural network), and derives a solar radiation predicted value from the feature vector obtained by the feature vector connection unit 53 using the neural network.

[0055] Here, this predicted solar radiation value is, for example, the global solar radiation (GHI: Global Horizontal Irradiance (GHIR) predictions.

[0056] 3 includes a neural network including an LSTM layer, which converts historical data on power generation conditions indicating power generation conditions at multiple points in time into feature vectors. These power generation conditions include solar radiation history (actual solar radiation data from multiple points in time up to the present), output history such as output voltage, output current, and output power (such as the output voltage, output current, and output power from the multiple points in time up to the present), temperature history (the temperature at the solar power generation facility from the multiple points in time up to the present), and solar panel specifications (such as the type of mounting system and solar panels at the solar power generation facility). Encoder 42-1 is specific to the solar power generation facility and is different for each solar power generation facility (i.e., it is machine-trained to be different for each solar power generation facility).

[0057] The encoder 42-2 has a neural network including an LSTM layer, and converts satellite forecast data into feature vectors that indicate weather forecast values ​​for multiple future points in time based on images taken by weather satellites at multiple past and / or present points in time. These weather forecast values ​​include solar radiation (GHI, DNI: Direct Normal Irradiance, EBH, DHI: Diffuse Horizontal Irradiance, etc.), cloud area ratio, cloud opacity, solar position (elevation angle and azimuth angle), temperature, etc. The encoder 42-2 is common to all solar power generation facilities (i.e., it has been machine-learned to be common to multiple solar power generation facilities).

[0058] The encoder 42-3 is equipped with a neural network including an LSTM layer, and converts weather forecast data, which indicates weather forecast values ​​for multiple future points in time, into a feature vector. The weather forecast values ​​include temperature, pressure, humidity, cloud cover ratio, precipitation, wind direction, wind speed, etc. The encoder 42-3 is common to all solar power generation facilities (i.e., it has been machine-learned to be common to multiple solar power generation facilities).

[0059] The encoder 42-4 includes a neural network including an LSTM layer, and converts the cloud area ratio forecast data, which indicates the cloud area ratio forecast values ​​at multiple future points in time, and the time data into a feature vector. The time data is the time value (e.g., the time of day) at the multiple points in time. The encoder 42-4 is common to all solar power generation facilities (i.e., it has been machine-learned to be common to multiple solar power generation facilities).

[0060] The data linking unit 43 links the predicted solar radiation value obtained by the solar radiation predicting unit 41 and the feature vectors generated by the encoders 42-1 to 42-4 to generate one feature vector.

[0061] The power generation prediction unit 44 includes a neural network, which derives predicted power generation values ​​at multiple future time points from the feature vector obtained by the data linking unit 43. The predicted power generation values ​​are predicted values ​​for the power generation amount of the photovoltaic power generation facility, and may be values ​​of power or energy. Here, the multiple future time points are time points that arrive at predetermined time intervals, such as 5-minute intervals, 15-minute intervals, or 30-minute intervals, within a period such as 3 hours, 6 hours, or 24 hours from the present time.

[0062] The machine learning processing unit 26 performs machine learning of a learning device (here, a neural network) in the solar power generation amount prediction unit 25 by an existing learning method (such as backpropagation). Specifically, the machine learning processing unit 26 updates the parameters of the learning device (here, the weights and biases of the neural network) by using learning data including multiple sets of pairs of input data and output data of the learning device.

[0063] The machine learning processing unit 26 performs machine learning in advance for the solar radiation prediction unit 41 individually for each power generation facility. Here, a solar radiation meter is installed in each power generation facility, and the actual measurement data of the solar radiation amount of each power generation facility is obtained by this solar radiation meter, and this is used as learning data for this machine learning.

[0064] The machine learning processing unit 26 performs machine learning on the learner in the photovoltaic power generation amount prediction unit 25 using the past weather forecast history data generated by the past forecast estimation unit 22 as input data (the above-mentioned weather forecast data).

[0065] Next, the operation of the solar power generation amount prediction system will be described.

[0066] (a) Forecast of solar power generation

[0067] As described above, the input data acquisition unit 24 acquires sky image history data, power generation condition history data, satellite forecast data, weather forecast data, and cloud area ratio forecast data as input data, and the solar power generation amount prediction unit 25 derives predicted solar power generation amounts at multiple future points in time from the input data.

[0068] (b) Machine learning of the solar power generation forecasting unit 25

[0069] (b1) Generation of training data

[0070] First, the past actual data acquisition unit 21 acquires historical weather data, cloud area ratio data, time history data, and solar position data for multiple past points in time. For example, the past actual data acquisition unit 21 acquires historical weather data and cloud area ratio data for multiple past points in time from an external server, and generates time history data and solar position history data for the multiple points in time.

[0071] Next, the past forecast estimation unit 22 derives weather forecast history data corresponding to the actual weather history data for multiple past points in time from the acquired actual weather history data, cloud area ratio history data, time history data, and solar position history data.

[0072] The cloud area ratio forecast data and the artificial satellite forecast data may also be generated by the past forecast estimation unit 22 in the same manner as the weather forecast data (that is, the above-mentioned weather forecast history data).

[0073] (b2) Machine Learning

[0074] The solar radiation prediction unit 41 is shared by multiple solar power generation facilities. The machine learning processing unit 26 first performs machine learning for the solar radiation prediction unit 41. At this time, pairs of sky image history data and actual solar radiation measurement values ​​for each solar power generation facility are used as learning data, and the learning data for the multiple solar power generation facilities is compiled and used for the machine learning of the solar radiation prediction unit 41.

[0075] Next, pairs of sky image history data, weather forecast data (i.e., the above-mentioned weather forecast history data), cloud area ratio forecast data, satellite forecast data, and power generation condition history data for multiple past points in time, and actual power generation amounts at multiple future points in time as viewed from those multiple past points in time, are used as learning data, and machine learning processing unit 26 uses the learning data to perform machine learning on solar power generation amount prediction unit 25. At this time, encoders 51 and 52 of solar radiation prediction unit 41 are not updated, and the results of machine learning by solar radiation prediction unit 41 are left as they are.

[0076] As described above, learning data is generated based on actual measurement data obtained for each of a plurality of solar power generation facilities, and the past forecast estimation unit 22 and the solar power generation prediction unit 25, which are common to the plurality of solar power generation facilities, are machine-learned based on the learning data.

[0077] As described above, according to the above embodiment, the past forecast estimation unit 22 estimates and generates past weather forecast history data using a learning device that uses past actual weather history data as input data. Here, the past actual weather history data is actual weather history data from multiple points in time in the past, and the past weather forecast history data is weather forecast history data from multiple points in time in the past. Then, the machine learning processing unit 26 performs machine learning on the learning device in the solar power generation amount prediction unit 25 using the past weather forecast history data generated by the past forecast estimation unit 22.

[0078] This makes it possible to estimate appropriate past weather forecast data (i.e., weather forecast history data) in a short time when predicting solar power generation using a learning machine that uses weather forecast data as input data, and therefore to perform appropriate machine learning in a relatively short time and begin to accurately predict solar power generation.

[0079] Furthermore, forecast values ​​at any point in the past can be estimated, and the past forecast estimation unit 22 can also estimate weather forecasts at locations (power generation facilities) where weather forecasts are not locally based in the first place, so a sufficient amount of learning data can be obtained for any location (power generation facility), and appropriate machine learning can be performed.

[0080] It should be noted that various changes and modifications to the above-described embodiments will be apparent to those skilled in the art. Such changes and modifications may be made without departing from the spirit and scope of the subject matter and without diminishing its intended advantages. In other words, it is intended that such changes and modifications be included within the scope of the claims.

[0081] For example, a device including the past actual data acquiring unit 21, the past forecast estimating unit 22, and the machine learning processing unit 23 in the above embodiment may be used as a past forecast estimation device. In this case, the past forecast estimation device does not need to include the input data acquiring unit 24, the solar power generation amount prediction unit 25, and the machine learning processing unit 26. Furthermore, the past weather forecast data obtained by the past forecast estimation device (and the past forecast estimation method executed in the past forecast estimation device) can be used for purposes other than predicting solar power generation.

[0082] In the above embodiment, the programs 11 and 12 may be recorded on a portable computer-readable recording medium and installed into the device from the recording medium. [Industrial Applicability]

[0083] The present invention is applicable to, for example, prediction of solar power generation. [Explanation of symbols]

[0084] 11 Past forecast estimation program 12 Solar power generation forecasting program 22 Past Forecast Estimation Section 23 Machine learning processing unit (an example of a second machine learning processing unit) 25. Photovoltaic Power Generation Forecasting Department 26 Machine learning processing unit (an example of the first machine learning processing unit)

Claims

1. a photovoltaic power generation amount prediction unit that predicts the photovoltaic power generation amount using a first learning device that uses weather forecast data as input data; a past forecast estimation unit that estimates and generates past weather forecast history data from past actual weather history data; a first machine learning processing unit that performs machine learning of the first learning device using the past weather forecast history data generated by the past forecast estimation unit; A solar power generation prediction system comprising:

2. the solar power generation amount prediction unit predicts the solar power generation amount using the first learning device, which receives as input data the weather forecast data and sky image history data obtained by photographing the sky with an imaging device from a power generation facility that is a target for predicting the solar power generation amount; The first learning device (a) generates solar radiation prediction data from the sky image history data, and (b) generates a predicted value of the solar power generation amount from the solar radiation prediction data and the weather forecast data; The solar power generation amount prediction system according to claim 1,

3. Further comprising a second machine learning processing unit, the past forecast estimation unit estimates and generates the past weather forecast history data from the past actual weather history data using a second learning device; the second machine learning processing unit performs machine learning of the second learner; The solar power generation amount prediction system according to claim 1,

4. a photovoltaic power generation amount prediction step of predicting the photovoltaic power generation amount using a first learning device that uses weather forecast data as input data; a past forecast estimation step of estimating and generating past weather forecast history data from past actual weather history data; a machine learning processing step of performing machine learning of the first learning device using the past weather forecast history data generated in the past forecast estimation step; A method for predicting solar power generation amount, comprising:

5. On the computer, a photovoltaic power generation amount prediction step of predicting the photovoltaic power generation amount using a first learning device that uses weather forecast data as input data; a past forecast estimation step of estimating and generating past weather forecast history data from past actual weather history data; a machine learning processing step of performing machine learning of the first learning device using the past weather forecast history data generated in the past forecast estimation step; A solar power generation prediction program that executes the above.

6. a past forecast estimation unit that estimates and generates past weather forecast history data using a learning device that uses past actual weather history data as input data; The past actual weather history data is actual weather history data at a plurality of points in time in the past, The past weather forecast history data is weather forecast history data at a plurality of past points in time; A past forecast estimation device characterized by the above.

7. The past forecast estimation device according to claim 6, wherein the past forecast estimation unit estimates and generates the past weather forecast history data using a learning device with the past actual weather history data, cloud area ratio history data, and solar position history data as input data.

8. the learning device is machine-learned using the past actual weather history data and past weather forecast history data of a specific weather forecast provider as learning data; the past forecast estimation unit estimates and generates the past weather forecast history data for the specific weather forecast provider; 7. The past forecast estimation device according to claim 6, wherein:

9. a past forecast estimation step of estimating and generating past weather forecast history data using a learning device that uses past actual weather history data as input data; The past actual weather history data is actual weather history data at a plurality of points in time in the past, The past weather forecast history data is weather forecast history data at a plurality of past points in time; A past forecast estimation method characterized by:

10. On the computer, a learning device that uses past actual weather history data as input data to estimate and generate past weather forecast history data; The past actual weather history data is actual weather history data at a plurality of points in time in the past, The past weather forecast history data is weather forecast history data at a plurality of past points in time; A past forecast estimation program that features:

Images