JP7043661B1 - Information processing equipment, information processing methods, programs and power generation systems - Google Patents

Abstract

PROBLEM TO BE SOLVED: To predict the amount of electric power generated by a power plant. An information processing device includes a position calculation unit, a power amount calculation unit, and an output unit. The location calculator was generated by one or more power plants for a first sample group containing multiple actual values for the first time zone on multiple reference dates for the amount of power generated by one or more power plants. The target position of the actual value in the first time zone on the target day of the electric energy is calculated. The electric energy calculation unit calculates the electric energy corresponding to the target position in the second sample group including multiple actual values of the prediction target time zone on multiple reference dates of the electric power generated by one or more power plants. do. The output unit outputs the electric energy corresponding to the target position as the predicted electric energy predicted to be generated by one or a plurality of power plants in the predicted target time zone. [Selection diagram] Fig. 1

Description

Embodiments of the present invention relate to information processing devices, information processing methods, programs and power generation systems.

The method of purchasing electricity generated by solar power generation will shift from a fixed-price purchase system (FIT) to a market price-linked purchase system (FIP). In the market price-linked purchase system, in order to match the planned value and the actual value of the amount of power generation, for example, the utilization of the market one hour before the electric power is traded one hour before the electric power supply is considered. For this reason, in the purchase system linked to the market price, it is required to improve the accuracy of the short-time prediction technology for predicting the amount of electric power to be generated in the relatively near future.

Conventionally, as a short-time prediction technique in photovoltaic power generation, there is a method of using only the actual power generation value and a method of using a meteorological satellite and a weather forecast in addition to the actual power generation value.

As a method of using only the actual power generation value, a continuous prediction method of the clear sky index is known. However, in the continuous prediction method of the clear sky index, the mutual conversion between the solar radiation intensity and the amount of power generation is complicated, and the error is large.

As a method of using a meteorological satellite and a weather forecast in addition to the actual power generation value, a method of searching for similar days of the weather is known. However, in this method, the data processing becomes complicated as the amount of data acquired from the outside increases, and as a result, the risk of problems such as the inability to acquire the data in real time increases.

Japanese Unexamined Patent Publication No. 2020-108188 Japanese Unexamined Patent Publication No. 2013-84736 Japanese Patent No. 6785971

Sokol Dervishi and Ardeshir Mahdavi, "COMPARISON OF MODELS FOR THE DERIVATION OF DIFFUSE FRACTION OF GLOBAL IRRADIANCE DATA FOR VIENNA, AUSTRIA", Proceedings of Building Simulation 2011: 12th Conference of International Building Performance Simulation Association, Sydney, 14-16 November, P. 765-771

An object to be solved by the present invention is to provide an information processing device, an information processing method, a program, and a power generation system that can easily and accurately predict the amount of electric power generated by a power plant using a small amount of data. be.

The information processing apparatus according to the embodiment includes a position calculation unit, a power amount calculation unit, and an output unit. The position calculation unit generates power from the one or more power plants with respect to a first sample group including a plurality of actual values in the first time zone on a plurality of reference days of the amount of power generated by the one or a plurality of power plants. The target position of the actual value in the first time zone on the target day of the calculated electric energy is calculated. The electric energy calculation unit corresponds to the target position in the second sample group including a plurality of actual values of the power amount generated by the one or a plurality of power plants in the prediction target time zone on the plurality of reference dates. Calculate the amount of power. The output unit outputs the electric energy corresponding to the target position as the predicted electric energy predicted to be generated by the one or more power plants in the prediction target time zone.

The figure which shows the functional structure of the prediction apparatus which concerns on 1st Embodiment. A flowchart showing the processing flow of the predictor. The figure which shows the actual value of the electric energy generated by a power plant for each time zone. The figure which shows the prediction target time zone. The figure which shows the actual value of the 1st time zone of a target day. The figure which shows the actual value of the 1st time zone of a plurality of reference days. The figure which shows the actual value of the prediction target time zone of a plurality of reference days. The figure which shows an example of the change of the actual value. The figure which shows the functional structure of the prediction apparatus which concerns on 2nd Embodiment. The figure which shows the block composition of a power plant model. The figure which shows the numerical example of Erbs, Orgill and Reindl which are direct dispersion models. The figure which shows the calculation example of the direct scattering separation model when Orgill is used. The figure which shows the numerical example in the direction of the sun. The figure which shows the numerical example of the illuminance intensity of an inclined surface. The figure which shows the calculation example of the sun direction. The figure which shows the difference between the module temperature and the ambient temperature. The figure which shows the conversion efficiency of an inverter with respect to the load factor. A flowchart showing the processing flow of the power plant model. The figure which shows the hardware configuration of a predictor.

Hereinafter, the prediction device 10 according to the embodiment will be described with reference to the drawings. The prediction device 10 calculates the amount of power generated by one or more power plants in the prediction target time zone based on the past amount of power generated by one or more power plants.

(First Embodiment)
FIG. 1 is a diagram showing a functional configuration of the prediction device 10 according to the first embodiment. The prediction device 10 is, for example, a single computer or a computer such as a server device. The prediction device 10 may be one computer or may be configured by a plurality of computers such as a cloud system. The computer functions as a predictor 10 by executing a predetermined program.

The prediction device 10 includes a receiving unit 22, a storage unit 24, an input unit 26, a target sample acquisition unit 28, a first sample group acquisition unit 30, a second sample group acquisition unit 32, and an actual value correction unit 34. The position calculation unit 36, the electric energy calculation unit 38, and the output unit 40 are provided.

The receiving unit 22 receives the actual value of the amount of electric power generated by the power plant for each time zone. The power plant is a solar power plant in this embodiment. The power plant may be another type of power plant such as a hydropower plant, a wind power plant, or a geothermal power plant. Further, the power plant may be a facility installed by a business operator such as an electric power company, or may be a private power generation device installed in a home or the like.

Further, the receiving unit 22 may receive the actual value of the amount of electric power generated by a plurality of power plants whose power generation can be estimated by the same power generation model for each time zone. For example, the receiving unit 22 has a time zone of the amount of electric power generated by a plurality of photovoltaic power plants using the same equipment in close locations, where the energy obtained from sunlight is almost the same and the weather conditions are also the same. You may receive the actual value for each.

The storage unit 24 stores the actual value for each time zone received by the reception unit 22. For example, the storage unit 24 is managed by a database and stores a date, a time zone, and an actual value as a set. By designating the date and time zone, the storage unit 24 searches for and outputs the actual value of the designated date and time zone. The storage unit 24 may be realized in the prediction device 10, or may be realized in a database server or the like outside the prediction device 10.

The input unit 26 accepts the input of the prediction target time zone on the prediction date. The input unit 26 may accept, for example, a prediction target time zone operated and input by the user, a prediction target time zone received from another device, or a periodically automatically input prediction target time. You may accept the band. The input unit 26 gives the received prediction target time zone to the second sample group acquisition unit 32 and the actual value correction unit 34.

The target sample acquisition unit 28 is a time zone before the current time among the actual values for each time zone stored by the storage unit 24, and is an actual value in one time zone in which substantial power generation is performed. To get. For example, the target sample acquisition unit 28 acquires the actual value in the latest time zone in which the actual power generation is performed among the actual values stored in the storage unit 24 for each time zone. Subsequently, the target sample acquisition unit 28 specifies the time zone of the acquired actual value as the first time zone. Further, the target sample acquisition unit 28 specifies the power generation date of the acquired actual value as the target date. The target sample acquisition unit 28 gives the specified first time zone to the first sample group acquisition unit 30 and the actual value correction unit 34. Further, the target sample acquisition unit 28 gives the acquired actual value to the position calculation unit 36 as an actual value in the first time zone on the target day.

The first sample group acquisition unit 30 acquires a first sample group including a plurality of actual values in the first time zone on a plurality of reference dates from the storage unit 24. Multiple reference dates are multiple days selected under predetermined rules prior to the predicted date. The first sample group acquisition unit 30 gives the first sample group to the actual value correction unit 34.

The second sample group acquisition unit 32 acquires a second sample group including a plurality of actual values of the prediction target time zone on a plurality of reference dates from the storage unit 24. The plurality of reference dates for which the second sample group acquisition unit 32 acquires the actual value are the same as the actual value in the first time zone acquired by the first sample group acquisition unit 30. The second sample group acquisition unit 32 gives the second sample group to the actual value correction unit 34.

The actual value correction unit 34 sets each of the plurality of actual values included in the first sample group into a target date calculation value calculated based on a predetermined power plant model and a reference date calculated based on the power plant model. Correct by the ratio with the calculated value. The power plant model is a model that calculates the electric power generated by the power plant or the value proportional to the electric power generated by the power plant. The target day calculation value is a target day power generated by the power plant in the corresponding time zone on the target day or a value proportional to the target day power calculated based on the power plant model. In addition, the reference date calculation value is proportional to the reference date power or the reference date power generated by the power plant in the corresponding time zone on the corresponding reference date among the plurality of reference dates calculated based on the power plant model. The value.

Further, the actual value correction unit 34 sets each of the plurality of actual values included in the second sample group to the target date calculated value calculated based on the power plant model and the reference date calculated value calculated based on the power plant model. It is corrected by the ratio with. The actual value correction unit 34 gives the corrected first sample group to the position calculation unit 36. Further, the actual value correction unit 34 gives the corrected second sample group to the electric energy calculation unit 38.

The position calculation unit 36 is the first on the target day of the electric energy generated by the power plant with respect to the first sample group including a plurality of actual values of the first time zone on the plurality of reference days of the electric energy generated by the power plant. Calculate the target position of the actual value in one time zone. In the present embodiment, the target position is the actual value of the first time zone on the target day in the data string in which a plurality of actual values included in the first sample group are arranged in the first order of either ascending order or descending order. It is the order of the amount of electric power corresponding to.

The ranking is not limited to a natural number and may be represented by a real value. Further, the rank may be a percentile rank standardized between 0% and 100%. The position calculation unit 36 gives the calculated target position to the electric energy calculation unit 38.

The electric energy calculation unit 38 calculates the electric energy corresponding to the target position in the second sample group including a plurality of actual values of the prediction target time zone on the plurality of reference days of the electric power generated by the power plant. Here, the electric power corresponding to the target position is the electric power corresponding to the target position in the data string in which a plurality of actual values included in the second sample group are arranged in the first order.

In the present embodiment, the electric energy calculation unit 38 sets the target position (rank) in the data string in which a plurality of actual values included in the second sample group are arranged in the first order as the electric energy corresponding to the target position. Calculate the corresponding electric energy. The electric energy calculation unit 38 gives the calculated electric energy to the output unit 40.

The output unit 40 outputs the electric power corresponding to the target position received from the electric energy calculation unit 38 as the predicted electric energy in the predicted target time zone to be generated.

FIG. 2 is a flowchart showing a processing flow of the prediction device 10. The processing flow of the prediction device 10 will be described with reference to the flowchart shown in FIG. 2 and FIGS. 3 to 7.

First, as shown in FIG. 3, the storage unit 24 stores the actual value of the amount of electric power generated by the power plant for each time zone. In the present embodiment, the storage unit 24 stores the electric energy every 30 minutes. More specifically, in the present embodiment, the storage unit 24 stores the electric energy from 00 minutes 00 seconds to 29 minutes 59 seconds and from 30 minutes 00 seconds to 59 minutes 59 seconds at each time. The time zone is not limited to every 30 minutes, but may be any time unit such as every 5 minutes, every 10 minutes, or every 60 minutes.

In S11, the input unit 26 accepts the input of the prediction target time zone on the prediction date. The prediction target time zone is a time zone for which the amount of electric power generated by the power plant is predicted. The input unit 26 accepts a time zone in the future from the current time as a prediction target time zone on the prediction date. The forecast target time zone corresponds to the time unit for acquiring the actual value. For example, the input unit 26 receives the prediction target time zone on the prediction date as shown in FIG. 4 at the current time as shown in FIG.

Subsequently, in S12, the target sample acquisition unit 28 was in the time zone before the current time among the actual values for each time zone stored by the storage unit 24, and substantially generated power 1 Get the actual value in one time zone. In the present embodiment, the target sample acquisition unit 28 acquires the actual value in the latest time zone in which the actual power generation is performed, among the actual values stored in the storage unit 24 for each time zone.

The time zone in which actual power generation is performed is not a time zone in which the actual value is 0 or a predetermined value or less, but a time zone in which the actual value is 0 or larger than the predetermined value. For example, when the current time is 13:10 and power is generated with an electric energy larger than a predetermined value from 12:30 to 12:59 on the predicted day, the target sample acquisition unit 28 is as shown in FIG. In addition, the actual value from 12:30 to 12:59 on the predicted date is acquired. Further, for example, when the current time is 8:00 and the power generation by the power plant is stopped from 17:00 to 8:59 the next morning, the target sample acquisition unit 28 will perform the target sample acquisition unit 28 at 16:00 on the day before the forecast date. Acquire the actual value in the time zone from 30 minutes to 16:59.

Subsequently, in S13, the target sample acquisition unit 28 specifies the time zone of the acquired actual value as the first time zone. Further, the target sample acquisition unit 28 specifies the power generation date of the acquired actual value as the target date. For example, when the actual value of the day of the predicted day is acquired, the target sample acquisition unit 28 specifies the day of the predicted day as the target day. Further, for example, when the actual value of the day before the predicted date is acquired, the target sample acquisition unit 28 specifies the day before the predicted date as the target day.

Subsequently, in S14, the first sample group acquisition unit 30 acquires the first sample group including a plurality of actual values in the first time zone on the plurality of reference dates from the storage unit 24. Multiple reference dates are multiple days selected under predetermined rules prior to the predicted date. In the present embodiment, the plurality of reference dates are 30 days included in the period from 1 day to 30 days before the predicted date. For example, if the predicted date is May 25, 2021, the first sample group acquisition unit 30 will have 30 days from April 25, 2021 to May 24, 2021, as shown in FIG. Is specified as multiple reference days, and the actual value of the first time zone of these days is acquired. It should be noted that the plurality of reference dates is not limited to such a period, and may be a plurality of days selected under other rules.

Subsequently, in S15, the second sample group acquisition unit 32 acquires the second sample group including a plurality of actual values of the prediction target time zone on the plurality of reference dates from the storage unit 24. The plurality of reference dates for which the second sample group acquisition unit 32 acquires the actual value are the same as the actual value in the first time zone acquired by the first sample group acquisition unit 30. For example, when the first sample group acquisition unit 30 acquires the actual values of the first time zone of 30 days from April 25, 2021 to May 24, 2021, the second sample group acquisition unit 30. As shown in FIG. 7, 32 acquires the actual values of the forecast target time zones of 30 days from April 25, 2021 to May 24, 2021.

Subsequently, in S16, the actual value correction unit 34 converts each of the plurality of actual values included in the first sample group into a target day calculation value calculated based on a predetermined power plant model and a power plant model. It is corrected by the ratio with the reference date calculated value calculated based on. More specifically, the actual value correction unit 34 sets each of the plurality of actual values included in the first sample group into the target day calculated value in the first time zone on the target day and the first time on the corresponding reference date. Correct by multiplying the ratio with the calculated value of the reference date of the band.

For example, the actual value correction unit 34 corrects as in the equation (1).

Actual value of the first time zone after correction = Actual value of the first time zone before correction x (Calculated value of the target day of the first time zone on the target day ÷ Calculated value of the reference date of the first time zone on the corresponding reference date ) ... (1)

Here, the power plant model is a model that calculates the electric power generated by the power plant or the value proportional to the electric power generated by the power plant. The target day calculation value is a value calculated based on the power plant model and is proportional to the target day power generated by the power plant in the corresponding time zone on the target day or the target day power. In addition, the reference date calculation value is the reference date power generated by the power plant in the corresponding time zone on the corresponding reference date among the plurality of reference dates calculated based on the power plant model, or the reference date power. It is a proportional value.

If the power plant is a solar power plant, the power plant model, for example, calculates the power generated by the power plant at the specified time on the target date or reference date based on facility information and weather information on the target date. Calculated as a value or a reference date calculated value.

Equipment information includes layout angle, module capacity, and inverter capacity. The layout angle is the normal direction of the solar cell module installed in the photovoltaic power plant. The layout angle may be represented by, for example, the orientation and tilt angle of the solar cell module. The module capacity is the maximum output of the solar cell module installed in the photovoltaic power plant. Inverter capacity is the maximum output of a DC / AC converter in a photovoltaic power plant.

The equipment information does not change day by day or time zone, and does not affect the ratio between the calculated value on the target day and the calculated value on the reference date. Therefore, the power plant model may use predetermined standardized values for the layout angle, the module capacity, and the inverter capacity. In this case, in the power plant model, the orientation of the solar cell module may be southward (0 °), and the inclination angle of the solar cell module may be about 30 ° to 40 °. Further, in the power plant model, the capacity of the solar cell module may be about 1.0 to 2.0, and the capacity of the inverter may be about 1.0. In addition, when the latitude of the installation position of the power plant is high, the tilt angle of the solar cell module may be larger than 30 ° to 40 ° in the power plant model.

Meteorological information includes, for example, all-sky plane solar radiation intensity, atmospheric top horizontal plane solar radiation intensity, sun direction, surface albedo, temperature and wind speed, and the like.

The total illuminance plane solar intensity is the solar radiation intensity with respect to the horizontal plane. The horizontal solar radiation intensity at the upper end of the atmosphere is the solar radiation intensity of the horizontal plane at the upper end of the atmosphere. The direction of the sun is a solid angle of the direction of the sun with respect to the installation position of the power plant, and is represented by the direction and altitude of the sun with respect to the installation position of the power plant. The surface albedo is the rate at which the surface of the earth reflects sunlight.

The actual value correction unit 34 may acquire the latitude, longitude, and time of the location of the power plant instead of the direction of the sun, and may calculate the direction of the sun based on the latitude, longitude, and time of the location of the power plant. In addition, the actual value correction unit 34 can acquire the total sky plane solar radiation intensity, the atmospheric upper surface horizontal plane solar radiation intensity, and the ground surface albedo from a meteorological database, a meteorological service server, or the like. Further, the actual value correction unit 34 can acquire the air temperature and the wind speed from the measuring device provided in the power plant. Further, the actual value correction unit 34 may acquire the air temperature and the wind speed from the weather database or the weather providing service server.

If the power plant model cannot acquire the surface albedo, the power generated by the power plant may be calculated using a value preset as the surface albedo. In addition, when the power plant model cannot obtain the total sky plane solar radiation intensity or the atmosphere upper surface horizontal plane solar radiation intensity, the total sky plane solar radiation intensity or the atmosphere upper surface horizontal plane solar radiation intensity is the average value of the area where the power plant is installed, etc. The power generated by the power plant may be calculated using a preset value. Further, the power plant model may calculate the electric power generated by the power plant by using the past average value when the temperature or the wind speed cannot be obtained.

Further, the solar radiation intensity for the solar cell module installed in the photovoltaic power plant is referred to as the inclined surface solar radiation intensity. The intensity of sunshine on the slope is approximately proportional to the power generated by the photovoltaic power plant. Therefore, the power plant model may calculate the sunshine intensity on the inclined surface as a value proportional to the electric power generated by the photovoltaic power plant. In this case, the power plant model calculates the illuminance intensity of the inclined surface at the specified time on the target day or the reference date as the target day calculation value or the reference date calculation value.

When calculating the sloping surface solar intensity, the solar cell module uses the facility information as well as the all-sky horizontal solar intensity, the upper-atmospheric horizontal solar intensity, the sun direction, and the surface albedo of the meteorological information. Even in this case, if the power plant model cannot acquire the surface albedo, the inclined surface solar radiation intensity may be calculated using a value preset as the surface albedo. In addition, if the power plant model cannot obtain the total illuminance plane solar intensity or the illuminance top horizontal plane solar radiation intensity, the average value of the area where the power plant is installed, etc. The illuminance intensity of the inclined surface may be calculated using a preset value.

An example of the power plant model will be described in detail later with reference to FIGS. 10 to 18.

Subsequently, in S17, the actual value correction unit 34 calculated each of the plurality of actual values included in the second sample group based on the target day calculation value calculated based on the power plant model and the power plant model. Corrected by the ratio with the reference date calculated value. More specifically, the actual value correction unit 34 sets each of the plurality of actual values included in the second sample group into the target day calculation value of the prediction target time zone on the target day and the prediction target time on the corresponding reference date. Correct by multiplying the ratio with the calculated value of the reference date of the band.

For example, the actual value correction unit 34 corrects as in the equation (2).

Actual value of the forecast target time zone after correction = Actual value of the forecast target time zone before correction x (Calculated value of the target day of the forecast target time zone on the target day ÷ Calculated value of the reference date of the forecast target time zone on the corresponding reference date ) ... (2)

The power plant model is the same as the model in which a plurality of actual values included in the first sample group are corrected in S16.

Subsequently, in S18, the position calculation unit 36 calculates the target position of the actual value in the first time zone on the target day of the amount of power generated by the power plant with respect to the corrected first sample group.

Here, the target position is the actual value of the first time zone on the target day in the data string in which a plurality of actual values included in the corrected first sample group are arranged in the first order of either ascending order or descending order. It is the order of the amount of power corresponding to the value. In the present embodiment, the position calculation unit 36 uses the electric power corresponding to the actual value of the first time zone on the target day in the data string in which a plurality of actual values included in the first sample group are arranged in ascending order as the target position. Calculate the order of quantity.

For example, when the first sample group includes N actual values (N is an integer of 2 or more), the position calculation unit 36 generates a data string in which N actual values are arranged as shown in equation (3). do.

Y [1] ≤ Y [2] ≤ Y [3] ≤ ... ≤ Y [N-2] ≤ Y [N-1] ≤ Y [N] ... (3)

Here, Y [·] represents the actual value included in the first sample group. The number in parentheses of Y [・] indicates the ranking.

The position calculation unit 36 compares, for example, the data strings arranged in this way with the actual value of the first time zone on the target day, and calculates the rank of the target position.

As an example, the position calculation unit 36 detects the value closest to the actual value in the first time zone on the target day in the data string. Then, the position calculation unit 36 may set the order of the detected values as the target position. Further, when the data string contains a plurality of values that are the same as the actual values in the first time zone on the target date, the position calculation unit 36 determines the order of the midpoints of the plurality of the same values as the target positions. May be. In this case, the position calculation unit 36 sets the order represented by the real value as the target position.

As another example, the position calculation unit 36 has a value of the highest rank below the actual value of the first time zone on the target day among a plurality of values included in the data column, and the value of the first time zone on the target day. Get the lowest rank value above the actual value. Then, the position calculation unit 36 may set the order obtained by linear interpolation based on the two acquired values as the target position.

Specifically, the actual value of the first time zone on the target day is X, and the value of the highest rank equal to or less than the actual value of the first time zone on the target day included in the first sample group is Y [n]. Let Y [n + 1] be the value of the lowest rank equal to or higher than the actual value in the first time zone on the target day included in the first sample group. In this case, the magnitude relation of X, Y [n] and Y [n + 1] is as shown in the equation (4).
Y [n] ≤ X ≤ Y [n + 1] ... (4)

Then, the position calculation unit 36 calculates nr, which is the order corresponding to the actual value in the first time zone on the target day, by calculating the equation (5).
nr = n × {(Y [n + 1] -X) / (Y [n + 1] -Y [n])} + (n + 1) × {X- (Y [n]) / (Y [n + 1] -Y [n] ])} ... (5)

The rank may be a percentile rank standardized between 0% and 100%.

Further, as another example, the position calculation unit 36 sets each of two or more predetermined time zones before the latest time zone as the first time zone, and targets each of the two or more predetermined time zones. The position may be calculated. Further, when the position calculation unit 36 has already calculated the target position in another time zone in the prediction processing of the past predicted electric energy, the position calculation unit 36 uses the target position in the prediction processing of the past predicted electric energy. May be read out. Then, the position calculation unit 36 calculates the average value of the calculated predetermined number of target positions, and outputs the calculated average value of the predetermined number of target positions as the target position of the actual value in the first time zone on the target day. .. As a result, the position calculation unit 36 can accurately calculate the predicted electric energy even when the actual value in the latest time zone changes suddenly. For example, when the actual value of the latest time zone fluctuates by a predetermined value or more from the time zone immediately before the latest time zone, the position calculation unit 36 sets such an average value as the first time on the target day. It may be output as the target position of the actual value of the band.

Subsequently, in S19, the electric energy calculation unit 38 calculates the electric energy corresponding to the target position in the corrected second sample group. Here, the electric power corresponding to the target position is the electric power corresponding to the target position in the data string in which a plurality of actual values included in the second sample group are arranged in the first order.

In the present embodiment, the electric energy calculation unit 38 corresponds to the target position (rank) in the data string in which a plurality of actual values included in the second sample group are arranged in ascending order as the electric energy corresponding to the target position. Calculate the amount of power to be used.

For example, when the second sample group includes N actual values, the electric energy calculation unit 38 generates a data string in which N actual values are arranged as in the equation (6).

Z [1] ≤ Z [2] ≤ Z [3] ≤ ... ≤ Z [N-2] ≤ Z [N-1] ≤ Z [N] ... (6)

Here, Z [·] represents the actual value included in the second sample group. The number in parentheses of Z [・] indicates the ranking.

The electric energy calculation unit 38 compares, for example, the data strings arranged in this way with the target position (rank) to calculate the power amount corresponding to the target position (rank).

As an example, the electric energy calculation unit 38 detects the actual value of the rank closest to the target position in the data string. Then, the electric energy calculation unit 38 may use the detected actual value as the electric energy corresponding to the target position (rank).

As another example, the electric energy calculation unit 38 has the actual value of the maximum rank below the target position (rank) and the minimum rank above the target position (rank) among the plurality of values included in the data column. Get the actual value. Then, the electric energy calculation unit 38 may use the electric energy obtained by linear interpolation based on the two acquired actual values as the electric energy corresponding to the target position.

Specifically, the target position (rank) is nr, the actual value of the maximum rank below the target position (rank) included in the second sample group is Z [n], and the target position included in the second sample group is set. Let Z [n + 1] be the actual value of the lowest rank above (rank). In this case, the magnitude relation of nr, n and (n + 1) is as shown in equation (7).
n ≦ nr ≦ (n + 1) ... (7)

Then, the electric energy calculation unit 38 calculates X [nr], which is the electric energy corresponding to the target position (rank), by calculating the equation (8).
X [nr] = Z [n] x {(n + 1) -nr} + Z [n + 1] x {nr-n} ... (8)

In S19 as well, the rank may be a percentile rank standardized between 0% and 100%.

Subsequently, in S20, the output unit 40 outputs the electric power corresponding to the target position (rank) calculated in S19 as the predicted electric energy predicted to be generated by the power plant in the predicted target time zone on the predicted date. do.

The prediction device 10 repeats the above processes from S11 to S20 every time the prediction target time zone is input.

In S18, when the first time zone on the target day is earlier than the preset time from the current time, the position calculation unit 36 may set the preset position (rank) as the target position.

For example, if the power generation period of a power plant in one day is from 9:00 to 16:59 and the current time is 8:00, the first time zone on the target day is from 16:30 to 17 on the previous day. It will be hour 59 minutes. In such a case, the first time zone on the target day is earlier than the preset time from the current time. Further, when the receiving unit 22 cannot receive the actual value due to a communication failure or the like for a preset time or longer, the first time zone on the target day is before the preset time or more from the current time.

In such a case, the correlation between the actual value of the first time zone on the target day and the expected power amount of the prediction target time zone becomes small, and the prediction device 10 can calculate the predicted electric energy with high accuracy. It may not be possible. Therefore, when the first time zone on the target day is earlier than the preset time from the current time, the predictor 10 predicts the electric energy by setting the preset position (rank) as the target position. The accuracy can be improved.

Further, in S18, when the first time zone on the target day is earlier than the preset time from the current time, the position calculation unit 36 has the highest frequency in the plurality of actual values included in the first sample group. The position (rank) may be the target position. Even in this way, the prediction device 10 can improve the prediction accuracy of the electric energy when there is a possibility that the predicted electric energy cannot be calculated accurately.

FIG. 8 is a diagram showing an example of a change in the actual value of each of the plurality of reference days and a change in the actual value of the target day.

The amount of power generated by a photovoltaic power plant varies from day to day, but the tendency of change in one day in the near season, for example, the last 30 days, is similar. Therefore, the order in which the electric energy in the first time zone is arranged in ascending order and the order in which the electric energy in the prediction target time zone is arranged in ascending order in a plurality of reference days such as the last 30 days are similar.

Therefore, the prediction device 10 calculates the target position (rank) of the actual value in the first time zone on the target day with respect to the plurality of actual values in the first time zone on the plurality of reference days, and predicts the target on the plurality of reference dates. Calculate the amount of power corresponding to the target position (rank) in multiple actual values in the time zone. Then, the prediction device 10 outputs the electric power corresponding to the target position as the predicted electric energy predicted to be generated in the prediction target time zone.

According to such a prediction device 10, the predicted power amount is calculated from the actual value of the power generated by the power plant, so that the predicted power amount can be calculated easily and accurately using a small number of types of data. can.

Further, the prediction device 10 uses the power plant model to correct a plurality of actual values in the first time zone on a plurality of reference dates and a plurality of actual values in the prediction target time zone on the plurality of reference dates. As a result, the prediction device 10 can correct the actual value based on the meteorological information including the direction of the sun and the like, so that it is possible to output a more accurate predicted electric energy.

(Second Embodiment)
Next, the prediction device 10 according to the second embodiment will be described. In the description of the second embodiment, the components having substantially the same configuration and function as the components described in the previous embodiments are designated by the same reference numerals, and detailed description is given except for differences. Omit.

FIG. 9 is a diagram showing a functional configuration of the prediction device 10 according to the second embodiment. The prediction device 10 according to the second embodiment further includes a position correction unit 52 as compared with the first embodiment.

The position correction unit 52 corrects the target position (rank) calculated by the position calculation unit 36 based on additional information such as meteorological information, and gives it to the electric energy calculation unit 38. For example, the position correction unit 52 corrects the target position (rank) based on the expected rate of change of the position in the predicted target time zone with respect to the position in the first time zone on the target day.

The position correction unit 52 may receive, for example, the meteorological information in the first time zone on the target day and the predicted meteorological information in the predicted target time zone on the predicted day, and calculate the expected rate of change. For example, the position correction unit 52 lowers the target position (rank) when the first time zone on the target day is fine, but the weather changes suddenly and it becomes rainy in the predicted target time zone. Correct to. Further, for example, the position correction unit 52 raises the target position (rank) when the first time zone on the target day is rainy, but the weather changes suddenly and the weather becomes fine in the prediction target time zone. Correct to do.

Since the prediction device 10 according to the second embodiment corrects the target position (rank) based on the difference between the weather information in the first time zone and the weather information in the prediction target time zone, the prediction device 10 is more accurate. The predicted power amount can be output.

(Power plant model)
Next, the power plant model of the photovoltaic power plant will be described.

FIG. 10 is a diagram showing a block configuration of a power plant model of a photovoltaic power plant. The power plant model receives the layout angle, module capacity and inverter capacity as equipment information. In addition, the power plant model receives as meteorological information the total sky level solar radiation intensity, the atmospheric top horizontal plane solar radiation intensity, the sun direction, and the surface albedo at the target time. Then, the power plant model calculates the electric power (kW) generated by the photovoltaic power plant at the target time.

The target time is the time for estimating the power. In the present embodiment, the target time is any time in the first time zone or any time in the prediction target time zone. For example, the target time may be the central time of the first time zone or the prediction target time zone.

The power plant model includes a solar radiation conversion unit 112, a temperature compensation unit 114, and a power conversion unit 116.

The solar radiation conversion unit 112 receives the layout angle, the total solar plane solar radiation intensity, the atmospheric upper horizontal plane solar radiation intensity, the sun direction, and the surface albedo. Based on this information, the solar radiation conversion unit 112 executes the direct scattering separation process and the inclined surface conversion process to calculate the inclined surface solar radiation intensity.

The temperature correction unit 114 receives the air temperature, the wind speed, and the insolation intensity of the inclined surface calculated by the insolation conversion unit 112. The temperature correction unit 114 calculates the temperature correction coefficient based on this information.

The power conversion unit 116 receives the module capacity, the inverter capacity, the illuminance intensity of the inclined surface calculated by the solar radiation conversion unit 112, and the temperature correction coefficient calculated by the temperature correction unit 114. The power conversion unit 116 calculates the power (kW) generated by the photovoltaic power plant based on this information.

(Direct scattering separation processing)
The power plant model deals with the sloping surface illuminance intensity, which is the illuminance intensity with respect to the sloping surface of the solar cell module. The solar radiation intensity handled in meteorological prediction and meteorological observation is the total illuminance plane solar radiation intensity, which is the solar radiation intensity with respect to the horizontal plane. Therefore, the power plant model converts the total illuminance plane solar intensity into the inclined surface solar radiation intensity.

In order to convert the total illuminance plane solar intensity into the inclined surface solar radiation intensity, the solar radiation conversion unit 112 first separates the total illuminance plane solar radiation intensity into a direct light component and a scattered light component by using a direct scattering separation model. Performs direct scattering separation processing. When the total sky horizontal solar radiation intensity is expressed as G, the direct light component is expressed as G _b , and the scattered light component is expressed as G _d , the relationship between G, G _b and G _d is expressed by the equation (11).

The direct scattering separation model calculates the proportion of scattered light components in the total illuminance plane solar intensity. The direct scattering separation model is an empirical formula that expresses the qualitative tendency that the scattered light component is small in fine weather, that is, the direct light component is large, and that the scattered light component is large, that is, the direct light component is small in cloudy weather. Is.

The total solar plane solar radiation intensity depends on the solar altitude in addition to the cloud cover. In order to remove the influence of the solar altitude, the direct-scattering separation model uses the clear sky index standardized by the solar plane solar radiation intensity at the upper end of the atmosphere, which is the solar plane solar radiation intensity at the upper end of the atmosphere. When the clear sky index is expressed as k and the atmospheric top horizontal plane solar radiation intensity is expressed as G ₀ , the clear sky index is expressed by the equation (12). k is a real number of 0 or more and 1 or less.

The direct dispersion model is represented by Eq. (13).

f _d (k) is a function for calculating the ratio of scattered light components in the total illuminance plane solar intensity based on the fine weather index. When k is small, k _d is large, and when k is large, k _d is small. It is a function that expresses the tendency.

The direct light component is represented by the formula (14).

From the above, the solar radiation conversion unit 112 executes the operations of equations (15-1), (15-2) and (15-3) in the direct scattering separation process to obtain the direct light component and the scattered light component. calculate.

FIG. 11 is a diagram showing numerical examples of Erbs, Orgill, and Reindl, which are direct dispersion models. All direct dispersal separation models of Erbs, Orgill and Reindl calculate approximate values. Therefore, the solar radiation conversion unit 112 can output an approximate calculation result regardless of which direct scattering separation model is used.

FIG. 12 is a diagram showing an operation example of a direct dispersion model when Orgill is used. The solar radiation conversion unit 112 executes an operation as shown in FIG. 12, for example, when using Orgill's direct scattering separation model.

(Inclined surface conversion process)
The dependence of the direct light component and the scattered light component on the sunshine intensity of the inclined surface changes depending on the relationship between the layout angle of the solar cell module and the direction of the sun. Equation (16) is a relational expression representing the illuminance intensity of the inclined surface in consideration of the angular relationship between the layout angle of the solar cell module and the direction of the sun.

S represents the illuminance intensity of the inclined surface. n ^ is a unit vector representing a solid angle (layout angle) in the normal direction of the solar cell module. s ^ is a unit vector representing a solid angle in the direction of the sun. z ^ is a unit vector representing a solid angle in the vertical direction. In the mathematical formulas, n ^, s ^, and z ^ are provided with hat symbols directly above the alphabet. Further, ρ represents the surface albedo and is the reflectance of the ground surface.

The first term on the right side of the equation (16) represents the direct light component with respect to the inclined surface of the solar cell module. The second term on the right side of the equation (16) represents a scattered light component with respect to the inclined surface of the solar cell module. The third term on the right side of the equation (16) represents the reflected light component with respect to the inclined surface of the solar cell module.

The direct light component with respect to the inclined surface is a directional solar radiation component, and becomes maximum when the normal direction (n ^) of the solar cell module coincides with the sun direction (s ^). That is, the value (G _b / (s ^, z ^)) obtained by normalizing the direct light component (G _b ) with respect to the horizontal plane by the solid angle (s ^, z ^) in the sun direction with respect to the vertical direction is the direct light component. It becomes the maximum value. Therefore, the first term on the right side of the equation (16) is a value obtained by multiplying the maximum value of the direct light component by the solid angle (s ^, n ^) in the sun direction with respect to the normal direction of the solar cell module.

The scattered light component with respect to the inclined surface is a non-directional solar radiation component, and is a solid angle averaged component (r ^, n ^) incident on the solar cell module with the same intensity from each direction (r ^) of the celestial sphere. It is proportional to the angle. Therefore, the scattered light component with respect to the inclined surface is proportional to the value represented by the equation (17).

In the equation (17), <・> _{r ^} represents a value obtained by averaging the solid angles in each direction (r ^) of the celestial sphere. Therefore, the second term on the right side of the equation (16) is a value obtained by multiplying the right side of the equation (17) by G _d .

The reflected light component for the inclined surface is a non-directional solar radiation component, and is the same as the scattered light component if the reflected light from the ground surface is interpreted as the scattered light having the intensity of the scattered light of ρG _d . Therefore, the third term on the right side of the equation (16) is a value obtained by multiplying the right side of the equation (17) by ρG _d .

From the above, the solar radiation conversion unit 112 calculates n ^, s ^, and z ^ based on the latitude and longitude, the time, and the layout angle of the photovoltaic power plant. Then, the solar radiation conversion unit 112 calculates the illuminance intensity of the inclined surface based on the relational expression of the equation (16).

FIG. 13 is a diagram showing a numerical example in the direction of the sun. FIG. 14 is a diagram showing a numerical example of the intensity of solar radiation on an inclined surface when the direction of the sun changes as shown in FIG.

In the examples of FIGS. 13 and 14, k is 0.8, and the latitude and longitude of the power plant are 35.00N and 135.00E. Further, in the examples of FIGS. 13 and 14, the direction from south to west is represented by 0 ° to 90 °, and the altitude from horizontal to zenith is represented by 0 ° to 90 °. In FIG. 14, the tilt angle of the solar cell module is changed by 0 °, 30 °, and 60 °, and the orientation of the solar cell module is set to 30 °. Therefore, in the example of FIG. 14, when the inclination angle is large, the direct light component does not reach in the early morning, and the illuminance intensity of the inclined surface becomes small.

FIG. 15 is a diagram showing an example of calculation in the direction of the sun. The direction of the sun can be calculated by functions that depend on latitude, longitude and time. The power plant model may calculate the sun direction using a function as shown in FIG. 15 based on the latitude, longitude and target time of the photovoltaic power plant.

(Calculation of temperature correction coefficient)
The efficiency of a photovoltaic power plant mainly depends on the conversion efficiency of the solar cell module. Generally, the lower the module temperature of a solar cell module, the higher the conversion efficiency. The module temperature is affected by the ambient temperature, wind speed and insolation intensity on the slope. The module temperature is close to the ambient air temperature when the inclined surface solar radiation intensity is weak, but is higher than the ambient temperature when the inclined surface solar radiation intensity is strong. Further, as for the module temperature, when the wind speed is high, the temperature rise due to solar radiation is suppressed.

When the inclined surface solar radiation intensity is S, the sloped surface solar radiation intensity absorption rate is a, the heat transfer efficiency is h, the ambient air temperature is T, and the module temperature is T _m , q, which is the heat flux escaping from the solar cell module, is It is expressed as the equation (18-1). Therefore, the module temperature T _m is expressed by the equation (18-2).

The heat transfer efficiency h generally increases with the wind speed, but cannot be easily calculated because it depends on the flow condition and the installation conditions. Therefore, the temperature compensating unit 114 may calculate the module temperature based on the empirical formula shown in the formula (19) including the inclined surface solar radiation intensity, the air temperature, and the wind speed. In equation (19), V is the wind speed. Further, in the equation (19), A and B are constants. For example, in equation (19), A is about 50 and B is about 0.4.

FIG. 16 is a diagram showing the difference between the module temperature calculated using the equation (19) and the ambient air temperature. The temperature correction unit 114 calculates the module temperature from the illuminance intensity and the wind speed on the inclined surface, for example, based on the numerical values shown in FIG.

Further, the output current-output voltage characteristic of the solar cell module is mainly characterized by the short circuit current and the open circuit voltage. The short-circuit current increases with the intensity of solar radiation on the inclined surface. However, the open circuit voltage decreases as the module temperature rises. The conversion efficiency of the solar cell module is a value obtained by dividing the generated power by the illuminance intensity of the inclined surface, and decreases as the temperature rises. The temperature correction coefficient of the solar cell module is the conversion efficiency standardized when the module temperature is 25.0 ° C.

The relationship between the temperature correction coefficient and the module temperature can be approximated by an empirical formula using the temperature coefficient. When the temperature correction coefficient is _KPV , the temperature correction coefficient is expressed by the equation (20). In addition, α is a value of about −0.4 / 100.

From the above, the temperature correction unit 114 calculates the module temperature and then calculates the temperature correction coefficient based on the equation (20). For example, the temperature correction coefficient is a numerical value that reduces the power generation efficiency by about 12% when the module temperature is 55 ° C.

(Power calculation process)
The main parameters of a photovoltaic power plant are module capacity and inverter capacity. The ratio of the module capacity to the inverter capacity is called an overload rate, and is set to a value of about 1.0 to 2.0 in order to increase the operating rate. In this case, the DC output power of the solar cell module is represented by the formula (21-1), and the AC output power of the inverter is represented by the formula (21-2).

Y _DC is the DC output power of the solar cell module. Y _AC is the AC output power of the inverter. C _PV is the module capacity. C _PCS is the inverter capacity. K _PV is the inverter conversion efficiency. η is the overload rate. min (x, y) is a function that selects the smaller value of x and y.

The module capacity is usually defined as the output power under the standard conditions of a module temperature of 25 ° C. and an inclined surface solar intensity of 1.0 kW / m ₂ . Therefore, the DC output power of the solar cell module is expressed by a simple calculation formula proportional to the illuminance intensity of the inclined surface.

The final output power of the photovoltaic power plant is the AC output power of the inverter. The AC output power of the inverter is a value obtained by limiting the DC output power of the solar cell module by the inverter capacity.

FIG. 17 is a diagram showing the conversion efficiency of the inverter with respect to the load factor. The power plant model may consider the conversion efficiency of the inverter to be approximately 1.0, which is a constant. However, the power plant model may calculate the inverter conversion efficiency using a function that includes empirical parameters. For example, the power plant model may calculate the inverter conversion efficiency using the functions of equations (22-1) and (22-2).

x represents a load factor. In equation (22-2), A, B and C represent empirical parameters. A is about 0.05. B is about 1.0. C is about 0.02. The function of equation (22-2) has a maximum value of 0/97 (K _PCS (x) = 1 / (B + 2√AC)) when the load factor is 0.63 (x = √ (C / A)). ). The power plant model can improve the power estimation accuracy at low load by calculating the inverter conversion efficiency using the function of Eq. (22-2).

(Processing flow of power plant model)
FIG. 18 is a flowchart showing a processing flow of the power plant model. To summarize the above description, the power plant model executes the process according to the flow shown in FIG.

First, in S51, the power plant model acquires the equipment information represented by the following equation (23).

The power plant model may acquire predetermined standardized values for the layout angle, the module capacity, and the inverter capacity.

Subsequently, in S52, the power plant model acquires the meteorological information represented by the following equation (24).

If the power plant model cannot acquire the surface albedo, the power plant model may acquire a value preset as the surface albedo. In addition, when the power plant model cannot obtain the total illuminance plane solar radiation intensity or the atmospheric top horizontal plane solar radiation intensity, the average value of the area where the power plant is installed is used as the total illuminance plane solar radiation intensity or the atmospheric top horizontal plane solar radiation intensity. You may get a preset value. Further, the power plant model may calculate the electric power generated by the power plant by using the past average value when the temperature or the wind speed cannot be obtained.

Subsequently, in S53, the power plant model calculates the following equations (25-1), (25-2), equations (25-3), and equations (25-4) to perform direct scattering separation processing. Execute.

Subsequently, in S54, the power plant model calculates the following equations (26-1), (26-2), equations (26-3), and equations (26-4) to perform the inclined surface conversion process. Execute. As a result, the power plant model can calculate the illuminance intensity (S) on the inclined surface.

Subsequently, in S55, the power plant model calculates the temperature correction coefficient by calculating the following equations (27-1) and (27-2).

Subsequently, in S56, the power plant model calculates the power output from the photovoltaic power plant by calculating the following equations (28-1) and (28-2).

Then, in S57, the power plant model outputs the electric power represented by the equation (29) as the target date calculated value or the reference date calculated value.

The power plant model may execute the processes from S51 to S54 and output the inclined surface solar radiation intensity (S) as a target date calculated value or a reference date calculated value. In this case, the power plant model does not have to acquire the temperature and wind speed at S52.

As described above, the power plant model can calculate the calculated value for correcting the plurality of actual values included in the first sample group and the second sample group.

(Hardware configuration)
FIG. 19 is a diagram showing an example of the hardware configuration of the prediction device 10 according to the embodiment. The prediction device 10 according to the present embodiment is realized by, for example, an information processing device having a hardware configuration as shown in FIG. The prediction device 10 includes a CPU (Central Processing Unit) 201, a RAM (Random Access Memory) 202, a ROM (Read Only Memory) 203, an operation input device 204, a storage device 206, and a communication device 207. Then, each of these parts is connected by a bus.

The CPU 201 is a processor that executes arithmetic processing, control processing, and the like according to a program. The CPU 201 executes various processes in cooperation with a program stored in the ROM 203, the storage device 206, or the like, using a predetermined area of the RAM 202 as a work area.

The RAM 202 is a memory such as an SDRAM (Synchronous Dynamic Random Access Memory). The RAM 202 functions as a work area of the CPU 201. The ROM 203 is a memory for storing programs and various information in a non-rewritable manner.

The operation input device 204 is an input device such as a mouse and a keyboard. The operation input device 204 receives the information input from the user as an instruction signal and outputs the instruction signal to the CPU 201.

The storage device 206 is a device for writing and reading data to a storage medium made of a semiconductor such as a flash memory, or a storage medium that can be magnetically or optically recordable. The storage device 206 writes and reads data to and from the storage medium in response to control from the CPU 201. The communication device 207 communicates with an external device via a network according to the control from the CPU 201.

The program executed by the prediction device 10 of the present embodiment includes a receiving module, an input module, a target sample acquisition module, a first sample group acquisition module, a second sample group acquisition module, an actual value correction module, and the like. It includes a position calculation module, a power amount calculation module, and an output module. In addition, the program may include a position correction module. This program is developed and executed on the RAM 202 by the CPU 201 (processor) to deploy the information processing apparatus on the receiving unit 22, the input unit 26, the target sample acquisition unit 28, the first sample group acquisition unit 30, and the second sample. It functions as a group acquisition unit 32, an actual value correction unit 34, a position calculation unit 36, an electric energy calculation unit 38, and an output unit 40. Further, this program may make the information processing apparatus function as the position correction unit 52. The prediction device 10 includes a receiving unit 22, an input unit 26, a target sample acquisition unit 28, a first sample group acquisition unit 30, a second sample group acquisition unit 32, an actual value correction unit 34, a position calculation unit 36, and an electric energy amount. At least a part of the calculation unit 38, the output unit 40, and the position correction unit 52 may be realized by a hardware circuit (for example, a semiconductor integrated circuit).

Further, the program executed by the prediction device 10 of the present embodiment is a file in a computer-installable format or an executable format, such as a CD-ROM, a flexible disk, a CD-R, or a DVD (Digital Versatile Disk). It is recorded and provided on a computer-readable recording medium.

Further, the program executed by the prediction device 10 of the present embodiment may be stored on a computer connected to a network such as the Internet and provided by downloading via the network. Further, the program executed by the prediction device 10 of the present embodiment may be configured to be provided or distributed via a network such as the Internet. Further, the program executed by the prediction device 10 may be configured to be provided by incorporating it into the ROM 203 or the like in advance.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

10 Predictor 22 Receiving unit 24 Storage unit 26 Input unit 28 Target sample acquisition unit 30 First sample group acquisition unit 32 Second sample group acquisition unit 34 Actual value correction unit 36 Position calculation unit 38 Electric energy calculation unit 40 Output unit 52 Position Correction part

Claims (20)

Target of the amount of power generated by the one or more power plants for the first sample group including a plurality of actual values in the first time zone on a plurality of reference days of the amount of power generated by one or more power plants. A position calculation unit that calculates the target position of the actual value of the first time zone on the day, and
The electric energy for calculating the electric energy corresponding to the target position in the second sample group including a plurality of actual values of the predicted target time zone on the plurality of reference days of the electric energy generated by the one or a plurality of power plants. Calculation unit and
An output unit that outputs the amount of power corresponding to the target position as the predicted amount of power predicted to be generated by the one or more power plants in the prediction target time zone.
Information processing device equipped with. The target position is the actual value of the first time zone on the target day in the data string in which a plurality of actual values included in the first sample group are arranged in the first order of either ascending order or descending order. It is the order of the corresponding electric energy,
The electric energy corresponding to the target position is the electric energy corresponding to the target position in a data string in which a plurality of actual values included in the second sample group are arranged in the first order. Information processing device. Each of the plurality of actual values included in the first sample group and each of the plurality of actual values included in the second sample group are the target date calculation value calculated based on a predetermined power plant model and the said. It is further equipped with an actual value correction unit that corrects by the ratio with the reference date calculation value calculated based on the power plant model.
The power plant model is a model for calculating a value proportional to the electric power generated by the one or more power plants or the electric power generated by the one or a plurality of power plants.
The target day calculation value is a target day power generated by the one or more power plants in the corresponding time zone on the target day or a value proportional to the target day power calculated based on the power plant model. can be,
The reference date calculation value is the reference date power generated by the one or more power plants in the corresponding time zone on the corresponding reference date among the plurality of reference dates calculated based on the power plant model. The information processing apparatus according to claim 1 or 2, which is a value proportional to the reference day power generation. The actual value correction unit
Each of the plurality of actual values included in the first sample group is the calculated value of the target day in the first time zone on the target day and the calculated value of the reference date in the first time zone on the corresponding reference date. Corrected by multiplying by the ratio with
Each of the plurality of actual values included in the second sample group is the calculated value of the target day in the first time zone on the target day and the calculated value of the reference date in the first time zone on the corresponding reference date. The information processing apparatus according to claim 3, which is corrected by multiplying the ratio with. Each of the one or more power plants is a photovoltaic power plant capable of estimating the power generated using the same power plant model.
The power plant model is a solar cell module with respect to an inclined surface based on a layout angle indicating the normal direction of the solar cell module, an all-sky horizontal plane solar radiation intensity, an atmospheric upper horizontal plane solar radiation intensity, a sun direction and a surface albedo. The information processing apparatus according to claim 4, which calculates the intensity of solar radiation on an inclined surface. The information processing device according to claim 5, wherein the power plant model calculates the inclined surface solar radiation intensity using a value preset as the surface albedo when the surface albedo cannot be acquired. If the power plant model cannot obtain the all-sky plane solar radiation intensity or the atmosphere top water plane solar radiation intensity, the inclined surface solar radiation uses a preset value as the all-sky plane solar radiation intensity or the atmosphere top water plane solar radiation intensity. The information processing apparatus according to claim 5 or 6, wherein the intensity is calculated. Each of the one or more power plants is a photovoltaic power plant capable of estimating the power generated using the same power plant model.
The power plant model is based on the layout angle indicating the normal direction of the solar cell module, all-sky plane solar radiation intensity, atmospheric top horizontal plane solar radiation intensity, sun direction, surface albedo, temperature and wind velocity, and is based on the one or more power plants. The information processing apparatus according to claim 4, wherein the electric power to be generated is calculated. The information processing according to claim 8, wherein the power plant model calculates the electric power generated by the one or a plurality of power plants by using a value preset as the surface albedo when the surface albedo cannot be acquired. Device. If the power plant model cannot obtain the total sky plane solar radiation intensity or the atmosphere upper surface horizontal plane solar radiation intensity, the power plant model may use one or more preset values as the total sky plane solar radiation intensity or the atmospheric upper surface horizontal plane solar radiation intensity. The information processing apparatus according to claim 8 or 9, wherein the electric power generated by the power plant of the above is calculated. The power plant model according to any one of claims 8 to 10, wherein when the temperature or the wind speed cannot be obtained, the electric power generated by the one or a plurality of power plants is calculated by using the past average value. Information processing equipment. The first time zone is the latest time zone in which electric power is generated by the one or more power plants.
The information processing apparatus according to any one of claims 2 to 11, wherein the prediction target time zone is a time zone after the first time zone on the target day. The information processing according to claim 12, wherein the position calculation unit sets a preset value as the target position when the first time zone on the target date is earlier than a preset time from the current time. Device. When the first time zone on the target day is earlier than a preset time from the current time, the position calculation unit determines the most frequent position among the plurality of actual values included in the first sample group. The information processing apparatus according to claim 12, which is the target position. The position calculation unit sets each of two or more predetermined time zones before the latest time zone in which electric power is generated by the one or a plurality of power plants as the first time zone, and sets the predetermined number of target positions. The information processing apparatus according to any one of claims 2 to 11, which is calculated and outputs the average value of the calculated predetermined number of the target positions as the target position of the actual value of the first time zone on the target day. .. 6. The information processing device described. The information according to claim 16, wherein the position correction unit calculates the predicted change rate based on the weather information in the first time zone on the target day and the predicted weather information in the predicted target time zone on the predicted date. Processing equipment. An information processing method executed by an information processing device.
The information processing device generates power from the one or more power plants for a first sample group including a plurality of actual values in the first time zone on a plurality of reference days of the amount of power generated by the one or a plurality of power plants. The target position of the actual value in the first time zone on the target day of the calculated electric energy is calculated.
The power corresponding to the target position in the second sample group including a plurality of actual values of the predicted target time zone on the plurality of reference dates of the amount of power generated by the information processing apparatus according to the description 1 or the plurality of power plants. Calculate the amount,
An information processing method in which the information processing apparatus outputs an electric power corresponding to the target position as a predicted electric energy predicted to be generated by the one or a plurality of power plants in the predicted target time zone. A program for making an information processing device function as a predictor for predicting electric power.
The information processing device
Target of the amount of power generated by the one or more power plants for the first sample group including a plurality of actual values in the first time zone on a plurality of reference days of the amount of power generated by one or more power plants. A position calculation unit that calculates the target position of the actual value of the first time zone on the day, and
The electric energy for calculating the electric energy corresponding to the target position in the second sample group including a plurality of actual values of the predicted target time zone on the plurality of reference days of the electric energy generated by the one or a plurality of power plants. Calculation unit and
An output unit that outputs the amount of power corresponding to the target position as the predicted amount of power predicted to be generated by the one or more power plants in the prediction target time zone.
A program that makes it work. With one or more power plants
An information processing device that predicts the amount of power generated by the one or more power plants, and
Equipped with
The information processing device is
Target of the amount of power generated by the one or more power plants for the first sample group including a plurality of actual values in the first time zone on a plurality of reference days of the amount of power generated by one or more power plants. A position calculation unit that calculates the target position of the actual value of the first time zone on the day, and
The electric energy for calculating the electric energy corresponding to the target position in the second sample group including a plurality of actual values of the predicted target time zone on the plurality of reference days of the electric energy generated by the one or a plurality of power plants. Calculation unit and
An output unit that outputs the amount of power corresponding to the target position as the predicted amount of power predicted to be generated by the one or more power plants in the prediction target time zone.
Power generation system with.

Images