阅读说明：本技术 提高风力发电站发电量预测精度的计算方法、装置和计算机设备 (Calculation method and device for improving power generation amount prediction accuracy of wind power station and computer equipment ) 是由 李原 赵雪楠 王松 徐国强 项颂 易善军 马继涛 尚国政 石永富 陈颖 尹洪全 于 2020-09-24 设计创作，主要内容包括：本发明为提高风力发电站发电量预测精度的计算方法、装置和计算机设备。其技术方案为：获取包含风力发电机的地理区域,将所述地理区域根据天气预测能力划分网格,依次获取所述网格内的风速预测值信息、所述网格内风力发电机性能信息和所述网格内风力发电机实际发电量；计算每个风力发电机的不同时段下的发电量预测值,将所述网格内所有风力发电机同一时段内的发电量预测值叠加,得到发电量预测初值；获取风力发电机实际发电值,将实际发电值与所述发电量预测初值比对相减,并将结果获取绝对值,输出误差值最小的所述发电量预测初值,并输出与所述发电量预测初值对应的网格,并将该网格所对应的发电量预测初值作为预测值输出。(The invention relates to a calculation method, a device and computer equipment for improving the prediction accuracy of the power generation amount of a wind power station. The technical scheme is as follows: acquiring a geographical area containing a wind driven generator, dividing the geographical area into grids according to weather prediction capability, and sequentially acquiring wind speed prediction value information in the grids, performance information of the wind driven generator in the grids and actual power generation amount of the wind driven generator in the grids; calculating the generating capacity predicted value of each wind driven generator in different time periods, and superposing the generating capacity predicted values of all the wind driven generators in the same time period in the grid to obtain an initial generating capacity predicted value; and acquiring an actual power generation value of the wind driven generator, comparing the actual power generation value with the initial power generation amount prediction value, subtracting the actual power generation value from the initial power generation amount prediction value, acquiring an absolute value of the result, outputting the initial power generation amount prediction value with the minimum error value, outputting a grid corresponding to the initial power generation amount prediction value, and outputting the initial power generation amount prediction value corresponding to the grid as a predicted value.)

1. A calculation method for improving the prediction accuracy of the generated energy of a wind power station is characterized by comprising the following steps:

acquiring a geographical area containing a wind driven generator, dividing the geographical area into grids according to weather prediction capability, and sequentially acquiring wind speed prediction value information in the grids, performance information of the wind driven generator in the grids and actual power generation amount of the wind driven generator in the grids;

acquiring the number of the wind driven generators in each grid;

acquiring operation information of each wind driven generator in each time period and a power curve in the time period;

calculating the generating capacity predicted value of each wind driven generator in different time periods, and overlapping the generating capacity predicted values of all the wind driven generators in the same time period in the grid to obtain an initial generating capacity predicted value in the time period of the grid; the calculation mode of the power generation capacity predicted value is to calculate the predicted value of the power generation capacity of the wind power station according to a power curve between the wind speed predicted value information and the power generation capacity of the wind driven generator;

obtaining actual power generation values of the wind driven generators in the grids at different time periods, comparing the actual power generation values in the same time period in the grids with the initial power generation amount prediction values, subtracting the actual power generation values from the initial power generation amount prediction values, obtaining an absolute value of a result, outputting the initial power generation amount prediction value with the minimum error value, outputting the grid corresponding to the initial power generation amount prediction value, and outputting the initial power generation amount prediction value corresponding to the grid as a predicted value;

and acquiring the grid quantity contained in the geographic area, calculating the grid quantity and the predicted value to obtain a total predicted value of the power generation amount of the wind power station in the geographic area, and outputting the total predicted value.

2. The calculation method for improving the prediction accuracy of the power generation amount of the wind power plant according to claim 1, wherein the step of sequentially acquiring the predicted wind speed information in the grid, the performance information of the wind power generators in the grid and the actual power generation amount of the wind power generators in the grid comprises:

the wind speed forecast information is weather forecast information of a weather forecast value such as wind speed received by a meteorological office.

3. The calculation method for improving the prediction accuracy of the power generation amount of the wind power plant according to claim 1, wherein the weather prediction capability is as follows: the capability of the weather bureau intelligent grid forecast service comprises a predicted time scale and a predicted network space resolution.

4. The calculation method for improving the power generation amount prediction accuracy of the wind power plant according to claim 3, wherein the step of obtaining the actual power generation values of the wind power generators in the grids at different time intervals, comparing the actual power generation values in the same time interval in the grids with the initial power generation amount prediction values, subtracting the actual power generation values from the initial power generation amount prediction values, obtaining an absolute value of the result to obtain an error value, outputting the initial power generation amount prediction value with the minimum error value, outputting the grids corresponding to the initial power generation amount prediction values, and outputting the initial power generation amount prediction values corresponding to the grids as predicted values comprises the steps of: and comparing the actual power generation result of the wind power station with the predicted value of each grid in the time period to obtain a predicted value with the minimum error, and selecting the predicted value obtained by calculation in the future time period of the corresponding grid as the predicted value of the power generation amount of the wind power station.

5. An apparatus for improving the accuracy of prediction of the power generation amount of a wind power plant, the apparatus comprising:

an input unit: the input unit acquires a geographical area containing a wind driven generator, grids are divided according to weather prediction capability of the geographical area, and the input unit sequentially acquires wind speed prediction value information in the grids, performance information of the wind driven generator in the grids and actual power generation amount of the wind driven generator in the grids;

the input unit acquires the number of the wind driven generators in each grid;

the input unit acquires operation information of each wind driven generator in each time period and a power curve in the time period;

a calculation unit: the computing unit computes the generating capacity predicted value of each wind driven generator in different time periods, and the computing unit superposes the generating capacity predicted values of all the wind driven generators in the same time period in the grid to obtain an initial generating capacity predicted value in the grid in the same time period; the calculation mode of the power generation capacity predicted value is to calculate the predicted value of the power generation capacity of the wind power station according to a power curve between the wind speed predicted value information and the power generation capacity of the wind driven generator;

a selection unit: the selection unit obtains actual power generation values of the wind driven generators in the grids at different time periods, the selection unit compares the actual power generation values in the same time period in the grids with the initial power generation amount prediction values to subtract, obtains absolute values from the results to obtain error values, selects the initial power generation amount prediction value with the minimum error value, selects the grid corresponding to the initial power generation amount prediction value, and outputs the initial power generation amount prediction value corresponding to the grid as a prediction value;

an output unit: the output unit obtains the grid number in the geographic area, the output unit calculates the grid number and the predicted value to obtain a total predicted value of the power generation amount of the wind power station in the geographic area, and the output unit outputs the total predicted value.

6. A computer device comprising a CPU, RAM, ROM and a program running on the CPU, characterized in that the program is executable to implement the functions of claims 1-5.

Technical Field

The invention relates to the technical field of wind power stations, in particular to a calculation method, a device and computer equipment for improving the prediction accuracy of the power generation amount of a wind power station.

Background

Due to the shortage of energy and the attention on environmental problems, wind energy is continuously developed and utilized as clean energy, and the wind power generation technology is continuously developed. However, because wind has the characteristics of volatility and randomness, the phenomenon of wind abandon is increasingly prominent, and the generated energy of a wind power station needs to be accurately predicted in order to improve the utilization rate of wind energy and the consumption level of the wind energy.

At present, various weather data including wind speed are generally substituted into a power conversion curve to generate a predicted power generation amount value, but this method is susceptible to a positional deviation or a time deviation of a weather prediction value, resulting in a prediction deviation. In addition, in a large-scale wind power plant, a large number of wind power generators are installed in an area of several square kilometers, the wind power generators are easily struck by lightning, and are susceptible to failure or shutdown due to strong wind or human factors, and the output of the wind power plant also changes significantly, which affects the accuracy of output prediction.

Disclosure of Invention

Aiming at the problems, the invention provides a calculation method for improving the prediction accuracy of the power generation amount of a wind power station, which comprises the following steps:

acquiring a geographical area containing a wind driven generator, dividing the geographical area into grids according to weather prediction capability, and sequentially acquiring wind speed prediction value information in the grids, performance information of the wind driven generator in the grids and actual power generation amount of the wind driven generator in the grids;

acquiring the number of the wind driven generators in each grid;

acquiring operation information of each wind driven generator in each time period and a power curve in the time period;

calculating the generating capacity predicted value of each wind driven generator in different time periods, and overlapping the generating capacity predicted values of all the wind driven generators in the same time period in the grid to obtain an initial generating capacity predicted value in the time period of the grid; the calculation mode of the power generation capacity predicted value is to calculate the predicted value of the power generation capacity of the wind power station according to a power curve between the wind speed predicted value information and the power generation capacity of the wind driven generator;

obtaining actual power generation values of the wind driven generators in the grids at different time periods, comparing the actual power generation values in the same time period in the grids with the initial power generation amount prediction values, subtracting the actual power generation values from the initial power generation amount prediction values, obtaining an absolute value of a result, outputting the initial power generation amount prediction value with the minimum error value, outputting the grid corresponding to the initial power generation amount prediction value, and outputting the initial power generation amount prediction value corresponding to the grid as a predicted value;

and acquiring the grid quantity contained in the geographic area, calculating the grid quantity and the predicted value to obtain a total predicted value of the power generation amount of the wind power station in the geographic area, and outputting the total predicted value.

Further, the step of sequentially acquiring wind speed predicted value information in the grid, performance information of the wind driven generator in the grid and actual power generation amount of the wind driven generator in the grid includes:

the wind speed forecast information is weather forecast information of a weather forecast value such as wind speed received by a meteorological office.

Further, the weather prediction capability is: the capability of the weather bureau intelligent grid forecast service comprises a predicted time scale and a predicted network space resolution.

Further, the step of obtaining the actual power generation values of the wind power generators in the grids at different time intervals, comparing the actual power generation values in the same time interval in the grids with the power generation amount prediction initial values, subtracting the actual power generation values from the power generation amount prediction initial values, obtaining an absolute value of the result, outputting the power generation amount prediction initial value with the minimum error value, outputting the grids corresponding to the power generation amount prediction initial values, and outputting the power generation amount prediction initial values corresponding to the grids as predicted values includes: and comparing the actual power generation result of the wind power station with the predicted value of each grid in the time period to obtain a predicted value with the minimum error, and selecting the predicted value obtained by calculation in the future time period of the corresponding grid as the predicted value of the power generation amount of the wind power station.

The invention also provides a device for improving the prediction precision of the power generation amount of the wind power station, which comprises the following components:

an input unit: the input unit acquires a geographical area containing a wind driven generator, grids are divided according to weather prediction capability of the geographical area, and the input unit sequentially acquires wind speed prediction value information in the grids, performance information of the wind driven generator in the grids and actual power generation amount of the wind driven generator in the grids;

the input unit acquires the number of the wind driven generators in each grid;

the input unit acquires operation information of each wind driven generator in each time period and a power curve in the time period;

a calculation unit: the computing unit computes the generating capacity predicted value of each wind driven generator in different time periods, and the computing unit superposes the generating capacity predicted values of all the wind driven generators in the same time period in the grid to obtain an initial generating capacity predicted value in the grid in the same time period; the calculation mode of the power generation capacity predicted value is to calculate the predicted value of the power generation capacity of the wind power station according to a power curve between the wind speed predicted value information and the power generation capacity of the wind driven generator;

a selection unit: the selection unit obtains actual power generation values of the wind driven generators in the grids at different time periods, the selection unit compares the actual power generation values in the same time period in the grids with the initial power generation amount prediction values to subtract, obtains absolute values from the results to obtain error values, selects the initial power generation amount prediction value with the minimum error value, selects the grid corresponding to the initial power generation amount prediction value, and outputs the initial power generation amount prediction value corresponding to the grid as a prediction value;

an output unit: the output unit obtains the grid number in the geographic area, the output unit calculates the grid number and the predicted value to obtain a total predicted value of the power generation amount of the wind power station in the geographic area, and the output unit outputs the total predicted value.

The invention also provides computer equipment which comprises a CPU, an RAM, a ROM and a program running on the CPU, and the functions of the calculation method and the device for improving the prediction accuracy of the generated energy of the wind power station can be realized when the program is executed.

Drawings

FIG. 1 is a schematic view of a wind power plant and its surrounding area with a power generation amount prediction apparatus according to an embodiment of the present invention.

Fig. 2 is a functional block diagram of an electric power generation amount prediction apparatus according to an embodiment of the present invention.

Fig. 3 is an operation flowchart of the power generation amount prediction apparatus according to the embodiment of the present invention.

Fig. 4 is an exemplary diagram of a wind speed prediction value input to the power generation amount prediction apparatus according to the embodiment of the present invention.

FIG. 5 is an exemplary graph of a power curve for converting wind speed into electrical energy for a wind turbine according to an embodiment of the present invention.

FIG. 6 is an exemplary graph illustrating calculation of a wind speed prediction value as power generation capacity according to an embodiment of the present invention.

FIG. 7 is a diagram illustrating an example of a predicted power generation result at a certain time according to an embodiment of the present invention.

FIG. 8 is a diagram illustrating an example of the power generation prediction results at different times after improving the accuracy according to the embodiment of the present invention.

Detailed Description

Weather prediction and geographical region partitioning

The weather data used for such predictions may be numerical forecast data provided by the chinese weather service. Currently, a weather forecast value for a 5km grid has been achieved. Therefore, in the present example, a side of 5km is taken as a grid range. It should be noted that if other weather forecast data is used, the defined grid range should match the prediction accuracy.

With reference to fig. 1, a wind power plant site is depicted, which is predicted by an embodiment of the invention, and the area comprising the wind power plant is gridded.

As shown in FIG. 1, a wind power plant 3 comprising wind generators 31-36 is provided. Each of the wind generators 31-36 may represent a single wind generator, or may represent multiple wind generators.

In the present embodiment, a side length of 5km is selected as the grid range, and therefore, the area including the installation position of the wind power plant 3 (the area surrounded by the thick line in fig. 1) is divided, as shown in fig. 1, the area including the wind power generation site 3 is divided into 56 grids a1 to G8 arranged in 8 rows and 7 columns, and the wind power generation site 3 is located inside the divided area surrounded by the grids of 5km range. Therefore, in the present embodiment, weather forecast data will be provided for the wind power plant 3 and for the surrounding area within 5 km. Of course, the area where the weather forecast data is provided may be extended to, for example, 10km outside the wind power plant 3, or may be reduced as appropriate. Further, the weather forecast data used for the prediction of the amount of power generation may be limited to the forecast data of the specific grid depending on the actual situation, and it is not necessary to use the weather forecast data of all the grids belonging to such an area for the prediction of the amount of power generation.

In the present embodiment, the predicted value of the wind speed is used, but other weather predicted values, such as predicted values of humidity and air pressure, may be used together.

Each part function of electric energy generation amount prediction device

The configuration of the electric power generation amount prediction device of the present embodiment will be described with reference to fig. 2, 4 to 6, 7A, and 8B. Fig. 2 is a block diagram showing the function of the electric power generation amount prediction device. Fig. 4 is a diagram showing an example of a wind speed predicted value input to the power generation amount prediction means.

Fig. 5 is a graph showing a relationship between wind speed and power generation amount of the wind turbine. Fig. 6 shows an example of calculating the wind speed predicted value as the power generation amount. Fig. 7A shows an example of a result of prediction of power generation amount at a certain time, and fig. 8B shows an example of a result of prediction of power generation amount at a different time from fig. 7A.

A first part: an input unit.

As shown in fig. 2, the power generation amount prediction method will include an input unit 11, a calculation unit 12, a selection unit 13, an output unit 14, and a storage unit 15. For convenience of explanation, assume that the latest weather forecast information is 0 at 12 months and 20 days in 2019: 00 (see fig. 4 and 6).

The input unit 11 is an input external data for the power generation amount prediction method. Specifically, the input unit 11 may receive weather forecast information such as a weather forecast value of wind speed from, for example, a weather bureau. In the present embodiment, it is assumed that prediction information, for example, weather prediction data from the current time to 9 hours later, is transmitted at predetermined time intervals (for example, every hour) for each of the 56 grids a1 to G8, distributed once every hour. (see FIG. 4). Here, the wind speed is determined by the magnitude in the north-south direction and the magnitude in the east-west direction as shown in fig. 4. And may also be determined by wind direction and size. The data of the wind speed prediction values used here are to be adapted to the height of the wind turbine nacelle. In the present embodiment, a predicted value of wind speed at a predetermined height of sea level 50m is used.

Furthermore, the input unit 11 also needs to receive information installed in the wind power plant 3, including receiving the wind power plant 3

Performance information of the power generation performance and operation information of the wind power generators, for example, information of a failure of the wind power generators 31 to 36 or an operation stop due to inspection or maintenance. In this embodiment, the performance information will be distributed over the same time interval (e.g., hourly) as the prediction information. But may be distributed at different time intervals (e.g., every 30 minutes) depending on the actual situation. It is to be noted that various information received by the input unit 11 will be stored in the storage unit 15.

In this embodiment, as described above, the user may provide the prediction information for all the grids in the prescribed area via an input means such as a keyboard, a touch panel, or network transmission. However, according to the actual situation, the input unit 11 may be designed to receive only weather prediction information corresponding to a specific grid related to the predicted power generation amount.

A second part: and a computing unit.

The calculation unit 12 will make a prediction of the amount of power generation from the prediction information (see fig. 4) of the predicted values of wind speeds in the 56 grids a1-G8 including the installation positions of the wind turbines 31-36. And converting the input wind speed predicted value, and calculating the predicted value of the generated energy.

Specifically, the computing unit 12 will first derive a north-south component V_yAnd east-west component V_xThe represented wind speed V is converted into an absolute value | V |. If the predicted wind speed is given by the magnitude and direction of the wind speed, no such conversion is required.

The calculation unit 12 calculates a wind speed prediction value | V ' | at the nacelle altitude of the wind turbine from the absolute value | V | of the predicted wind speed using the calculation formula stored in the storage unit 15, and when the heights of the nacelles of the wind turbines 31 to 36 are different, the wind speed prediction value | V ' | is calculated to be | V '₁|-|V′₆L. The dayWhen the air prediction gives data of wind speed at the height of the nacelle of the wind turbine, the above conversion process is not required, and | V | ═ V' |.

From the calculated predicted value | V' | of the wind speed, the calculation unit 12 substitutes it into the power conversion curve shown in fig. 5, converting it into the amount of power generation. For example, when the predicted value | V 'of the wind speed of the operating wind power generators 31 to 36 is used'₁|-|V′₆In | time, the predicted values for each wind speed are applied to the power curve. And adding the predicted values of the power generation capacity of the wind driven generators to obtain the predicted value of the power generation capacity of the wind power station 3. In this case, the accuracy of the prediction can be improved if a different power curve is used for each wind turbine. Therein, the wind power generator information in operation, the power conversion information on the wind power generators 31-36, etc. are stored in the storage unit 15. The calculation unit performs the corresponding calculation based on the information in the storage unit 15.

In the present embodiment, the calculation unit 12 performs the prediction calculation of the amount of power generation each time the input unit 11 receives the prediction information. As described above, for each of the 56 grids, the prediction information of the amount of power generation of the wind power plant 3 at the hourly intervals from the current time to 9 hours later is obtained, and thus one calculation operation will obtain 560(56 × 10) calculated values (see fig. 6). The power generation amount predicted value calculated in this manner is stored in the storage unit 15.

And a third part: and a selection unit.

Based on the predicted values of the amounts of power generation in the plurality of grids calculated as described above, the selection means 13 compares the actual result of power generation in the wind power plant 3 with the predicted value of power generation in that time, and selects the grid corresponding to the predicted value with the smallest error result. Then, a predicted value of the power generation amount at a future time is calculated in the grid and is used as a predicted value of the power generation amount of the wind power plant 3.

For example, fig. 4 shows the forecast information published at 12 months, 20 days and 0 years in 2019, which includes the wind speed forecasts of grids a1, a2, … A8 and … G8. According to the calculation unit 12, the calculated predicted values of the power generation amounts are 550kW, 538kW, … kW, … kW, as shown in fig. 6. When the actual power generation amount of the wind power plant 3 is 510kW when 0 of 12, 20 and 2019 is notified, the selection unit 13 compares the actual power generation amount with the above 56 power generation amount prediction values, respectively. The predicted power generation amount 513kW of the grid A8 is determined to have the smallest error from the actual power generation amount 510 kW. The selection unit will select the predicted value of the power generation for the future period of time after grid A8 as the predicted value of the power generation of the wind power plant 3, as shown in fig. 7A.

In the present embodiment, each time the actual power generation amount information of the wind power generation site 3 is obtained, the selection unit 13 compares the actual power generation amount result with the 56 power generation amount predicted values of the time slot, selects the grid corresponding to the predicted value having the smallest error compared with the actual power generation amount, and uses the predicted value of the power generation amount of the grid at the future time as the power generation amount predicted value of the wind power generation site 3. Therefore, the selected grid can be changed at predetermined time intervals according to the actual power generation situation, and the predicted value of the amount of power generation at the future time will also be changed. In the example of fig. 6 described above, it is assumed that the actual power generation amount result 820kW at 12 months and 20 days 1 in 2019 is obtained before the predicted value of the wind speed changes. In this case, the predicted value of the amount of electricity generation at 12 months and 20 days 1 in 2019 obtained from fig. 6 is: (a1, a2, … A8, B1, … G8) ═ (538, 513, … 788, 663, … 833). Then, since the predicted result of the power generation amount at time 1 in the grid G8 is closest to the actual power generation amount result, the selection unit 13 will change the selection to take the predicted value of the power generation amount of the future period of the grid G8 as the predicted value of the power generation of the wind power plant 3, as shown in fig. 8B.

The fourth part: and an output unit.

The output unit 14 outputs the power generation amount prediction value calculated by the calculation unit 12 after the selection unit 13 selects the area. For convenience of observation, the output unit 14 may be provided in the form of a table or a graph to output the prediction value. Fig. 7A and 8B show the power generation prediction values output by the output unit 14.

The fifth part is that: memory cell

The storage unit 15 will store the following:

(1) the wind speed prediction information received by the input unit 11 is stored.

(2) Information on the actual power production of the wind power plant 3 is stored, as well as on the cabin altitude of the wind turbines 31-36, the corresponding power curves of the wind turbines 31-36 and on the operational operation of the wind turbines 31-36.

(3) The predicted values of the power generation amounts for the respective grids and the respective time periods calculated by the calculation unit 12 are stored.

(4) Programs for executing the respective functions of the electric power generation amount prediction apparatus 1 are stored.

The functions of the input unit 11, the calculation unit 12, the selection unit 13, the output unit 14, and the storage unit 15 described above are realized by a computer including a CPU, a RAM, and a ROM.

Operation of power generation amount prediction device

According to the above description of the units of the device, the power generation amount prediction device operates as follows, and its flowchart is shown in fig. 3.

When the power generation amount prediction apparatus 1 selects a wind power plant to be predicted, first, in step S1, a geographical grid from which a wind speed prediction value is to be obtained is divided. In the present embodiment, the selected grid is 56 grids A1-G8 belonging to an area 5km outside the wind power plant 3. By using the method, the predicted value error caused by the position deviation and the time deviation of the weather predicted value can be reduced, and the prediction precision is improved. Under the actual condition, an operator can change the divided grids according to the self requirement and adjust the grid containing range and the grid size, so that the efficiency and the speed of calculation processing are improved, and meanwhile, an accurate predicted value can be obtained.

In step S2, the wind speed prediction value of each grid is calculated to obtain a prediction value of the power generation amount of the wind power plant, and the calculation unit 12 executes the calculation. In the calculation of the power generation amount, the operation information of the wind power generators 31 to 36 belonging to the wind power plant 3 is used. Therefore, the prediction device can take into account the state of the wind turbine when the wind turbine fails, and can improve the accuracy of the prediction.

In step S3, the calculated power generation amount predicted value for each grid is compared with the actual power generation amount of the wind power plant 3. And taking the power generation predicted value with the minimum error, and taking the predicted value of the future time slot in the corresponding grid as the power generation predicted value of the wind power station 3. The selection of the prediction value is performed by the selection unit 13.

In step S4, the predicted value of the selected power generation amount is output to the display device via the output unit 14. As a result, the system operator may use highly accurate predictive values to operate the system based on the most up-to-date information.

As described above, in the present embodiment, the prediction error due to the operation stop of the wind turbine at the wind power plant 3 can be reduced by using the operation information of each generator at the wind power plant 3; the set range of the grid A1-G8 is selected in a larger area of an installation site of the wind power station 3, the power generation predicted value with the minimum error is selected according to the actual power generation amount, and the power generation predicted value of the corresponding grid in the future time period is used as the predicted power generation amount of the wind power station 3, so that the prediction error caused by the position deviation or the time deviation of the weather forecast value can be reduced; the predicted value of the power generation amount is updated every time the actual power generation result of the wind power plant 3 is inputted, and the prediction accuracy is improved. This enables the follow-up planning to be performed efficiently and stably.

The calculation unit 12 calculates a power generation amount prediction value using a power curve of a conversion relationship between the wind speed and the power generation amount of the respective wind power generators, so that the power generation amount can be predicted from the characteristics of each wind power generator; the predicted value of the power generation amount is calculated using the predicted value of the wind speed at the nacelle height of the wind power generator, so that the predicted amount of power generation can be calculated under a condition close to the wind power actually received by the wind power generator. The accuracy of the prediction can be improved.

The calculation unit 12 calculates a power generation amount prediction value at predetermined time intervals, the selection unit 13 selects the prediction value after the calculation is completed, and the output unit 14 outputs the selected prediction value. As a result, the predicted value of the power generation is periodically updated, so that a more accurate predicted value can be provided. In addition, it may be automated to improve the efficiency of the predictive operation.

The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or applied directly or indirectly to other related technical fields, are included in the scope of the present invention.