Wind power generation amount prediction system, wind power generation amount prediction method, and program

Abstract

To provide a wind power generation amount prediction system that can improve prediction accuracy of a short term wind power generation amount.SOLUTION: A wind power generation amount prediction system according to an embodiment comprises: a wind state observation unit that measures a wind state of a prediction target wind farm of a wind power generation amount; a wind farm monitoring control unit that records measurement data which is measured at an installation position of a wind mill within the prediction target wind farm; a weather prediction data acquisition unit that acquires weather prediction data in an area including the prediction target wind farm; a storage unit that stores wind state observation data indicating a measurement result of a wind state, measurement data, and weather analysis data indicating an analysis result of the weather prediction data; and a prediction unit that respectively predicts a wind state of a first period which includes a prediction period of the wind power generation amount and a wind state of a second period which includes the prediction period and is shorter than the first period using data stored in the storage unit, and predicts the wind power generation amount on the basis of wind state prediction results of the first period and the second period.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to a wind power generation amount prediction system, a wind power generation amount prediction method, and a program.

Background Art

[0002] Conventionally, a system for predicting weather using meteorological prediction data such as wind conditions has been known. The meteorological prediction data calculated by this system can be used in various scenarios affected by the weather. For example, in the scenario of predicting the power generation amount of a wind power plant, the meteorological prediction data can be used.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the full liberalization of retail electricity, power generation companies and retail companies dealing with renewable energy such as wind power generation need to improve the prediction accuracy of their power generation amounts, which is important for business viability and grid stability.

[0005] However, meteorological prediction models such as the WRF model (Weather Research and Forecasting model) used for predicting wind power generation amounts are generally models for predicting wind speeds and the like over a long period. Therefore, they are not suitable for short-term power sales, and it may be necessary to frequently modify the power generation plan.

[0006] Therefore, the problem to be solved by the present invention is to provide a wind power generation amount prediction system, a wind power generation amount prediction method, and a program capable of improving the prediction accuracy of short-term wind power generation amounts.

Means for Solving the Problems

[0007] A wind power generation forecasting system according to one embodiment includes: a wind condition observation unit that measures the wind conditions of a wind farm to be forecasted; a wind farm monitoring and control unit that records measurement data measured at the wind turbine installation locations within the wind farm to be forecasted; a weather forecast data acquisition unit that acquires weather forecast data for an area including the wind farm to be forecasted; a storage unit that stores wind condition observation data showing the measurement results of wind conditions, measurement data, and weather analysis data showing the analysis results of weather forecast data; and a forecasting unit that uses the data stored in the storage unit to forecast the wind conditions for a first period including the wind power generation forecasting period and the wind conditions for a second period including the forecasting period but shorter than the first period, and forecasts the amount of wind power generation based on the wind condition forecasting results for the first and second periods. [Effects of the Invention]

[0008] According to this embodiment, it is possible to improve the accuracy of predicting wind power generation amounts over a short period of time. [Brief explanation of the drawing]

[0009] [Figure 1] This block diagram shows the configuration of a wind power generation prediction system according to one embodiment. [Figure 2] This figure shows an example of the structure of a wind condition observation database. [Figure 3] This figure shows an example of the structure of a SCADA database. [Figure 4] This is a diagram showing a part of the structure of a weather analysis database. [Figure 5] This is a block diagram showing the configuration of the prediction unit. [Figure 6] This flowchart shows the operating procedure for wind power generation prediction in the wind power generation prediction system. [Figure 7] (a) is a schematic diagram showing the spatial resolution of weather forecast data, (b) is an example of weather forecast data, (c) is a schematic diagram showing the spatial resolution of meteorological analysis data, and (d) is an example of meteorological analysis data. [Figure 8] This is a schematic diagram illustrating an example of a long-term prediction method used in the long-term prediction section. [Figure 9] This is a schematic diagram illustrating an example of a short-term prediction method used in the short-term prediction section. [Figure 10] This is a schematic diagram illustrating an example of a power generation prediction method used by the power generation prediction unit. [Figure 11] This is a block diagram showing the configuration of the prediction unit related to the first modified example. [Figure 12] This graph shows an example of comparing the predicted and measured wind speed results in the first modified example. [Figure 13] This is a block diagram showing the configuration of the prediction unit related to the second modified example. [Figure 14] This diagram schematically shows the arrangement of wind turbines in a wind farm in the second modified example. [Figure 15] This figure shows an example of wind speed changes between the upstream and wake wind turbines in the second modified example. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. The embodiments described below are not intended to limit the present invention.

[0011] Figure 1 is a block diagram showing the configuration of a wind power generation forecasting system according to one embodiment. The wind power generation forecasting system 1 shown in Figure 1 comprises a wind condition observation unit 100, a wind farm monitoring and control unit 200, a weather forecast data acquisition unit 300, a data analysis processing unit 500, a storage unit 600, and a forecasting unit 700. In the wind power generation forecasting system 1, the wind condition observation unit 100, the wind farm monitoring and control unit 200, and the weather forecast data acquisition unit 300 are connected to the data analysis processing unit 500 via a communication network 400, respectively.

[0012] In the wind power generation prediction system 1, the data analysis processing unit 500, the storage unit 600, and the prediction unit 700 may be provided as independent devices, or each unit may be provided within one server device. Further, the data analysis processing unit 500 and the prediction unit 700 may be provided within this server device, and the storage unit 600 may be provided as a device independent of the server device.

[0013] The wind condition observation unit 100 includes a measurement unit 110 and a measurement control unit 120. The measurement unit 110 measures the wind condition by, for example, Scanning LiDAR (Light Detection And Ranging). LiDAR is a measuring instrument that emits laser light into the atmosphere, receives scattered light from the atmosphere, and observes the wind speed and wind direction from its Doppler frequency. This wind condition measurement does not necessarily need to be by Scanning LiDAR, and any means for measuring the upper-air wind condition such as an observation mast or vertical LiDAR may be used. At least one or more measurement units 110 are installed at an arbitrary position within the wind farm to be predicted for wind power generation and its surrounding area.

[0014] The measurement control unit 120 sets the measurement conditions of the measurement unit 110. The measurement conditions include, for example, the measurement range, measurement position, measurement frequency, etc. It is desirable that the measurement conditions can be remotely changed, for example, via the communication unit 510 of the data analysis processing unit 500, but this is not necessarily the case. Further, the measurement control unit 120 may extract wind direction information from the measurement data of the measurement unit 110 and change the measurement position of the measurement unit 110 so as to measure the wind condition at a wind turbine located upstream (windward) within the wind farm or at a position in front of it.

[0015] The wind farm monitoring control unit 200 acquires SCADA (Supervisory Control and Data Acquisition) data for each wind turbine installed in the wind farm. The SCADA data includes measurement data such as the wind speed, wind direction, and power generation amount of the wind turbine at the installation position of the wind turbine.

[0016] The weather forecast data acquisition unit 300 acquires, for example, weather forecast GPV (Grid Point Value) data, which is weather forecast data distributed by the Japan Meteorological Agency. Weather forecast GPV data is past and future weather forecast data calculated by a supercomputer at grid points predetermined on a map. Note that the weather forecast data acquired by the weather forecast data acquisition unit 300 does not necessarily have to be of only one type.

[0017] The data analysis processing unit 500 includes a communication unit 510, a data processing unit 520, and a weather forecast data analysis unit 530. The individual parts of the data analysis processing unit 500 will be described below.

[0018] The communication unit 510 functions as a communication interface when communicating data with the wind condition observation unit 100, the wind farm monitoring and control unit 200, and the weather forecast data acquisition unit 300 via the communication network 400. Furthermore, the communication unit 510 transfers data acquired from the wind condition observation unit 100 and the wind farm monitoring and control unit 200 to the data processing unit 520, and also transfers weather forecast data acquired from the weather forecast data acquisition unit 300 to the weather forecast data analysis unit 530.

[0019] The data processing unit 520 performs primary processing of wind condition observation data measured by the wind condition observation unit 100. Primary processing of wind condition observation data includes, for example, performing processes such as vector synthesis and vector averaging on the line-of-sight wind speed measured by the wind condition observation unit 100 to calculate wind speed, wind direction, turbulence intensity, wind direction standard deviation, etc., in the horizontal and vertical directions at the measurement location.

[0020] Furthermore, the data processing unit 520 also performs primary processing of SCADA data measured by the wind farm monitoring and control unit 200. Primary processing of SCADA data includes, for example, classifying the SCADA data by referring to the operating status of the wind turbines, and calculating the wind speed ratio between the wind speed of wind turbines located upstream and those located downstream within the wind farm by referring to wind direction information.

[0021] The weather forecast data analysis unit 530 has a function to output weather analysis data showing the analysis results after adjusting the temporal and spatial resolution of the weather forecast data acquired from the weather forecast data acquisition unit 300. The weather forecast data analysis unit 530 can increase the spatial and temporal resolution of the weather analysis data compared to the weather forecast data by performing nesting using, for example, a WRF analysis model such as a numerical weather model.

[0022] The memory unit 600 includes a wind condition observation database 610, a SCADA database 620, and a meteorological analysis database 630. Each database will be described below.

[0023] Figure 2 shows an example of the structure of the wind condition observation database 610. The wind condition observation database 610 stores the results of the primary processing of wind condition observation data by the data processing unit 520. The wind condition observation database 610 shown in Figure 2 stores the time measured by the wind condition observation unit 100, the latitude, longitude, and altitude of the measurement point, the horizontal wind speed, the horizontal wind direction, the turbulence intensity, etc.

[0024] Figure 3 shows an example of the structure of the SCADA database 620. The SCADA database 620 stores the results of the primary processing of SCADA data by the data processing unit 520. The SCADA database 620 shown in Figure 3 stores the time measured by the wind farm monitoring control unit 200, the number of the wind turbine being monitored, the horizontal wind speed, the horizontal wind direction, various data related to the wind turbine such as the amount of power generated, and the wake state and inflow wind speed ratio calculated by the data processing unit 520.

[0025] Figure 4 shows a part of the structure of the meteorological analysis database 630. The meteorological analysis database 630 stores meteorological analysis data that shows the results of the meteorological forecast data analysis unit 530's analysis of meteorological forecast data. The meteorological analysis database 630 shown in Figure 4 stores the forecast time indicated in the meteorological forecast data, the analysis location, the altitude of the analysis location, and the north-south wind, east-west wind, atmospheric pressure, etc., at each altitude.

[0026] Figure 5 is a block diagram showing the configuration of the prediction unit 700. The prediction unit 700 includes a short-term prediction unit 710, a long-term prediction unit 720, a power generation prediction unit 730, and a result display unit 740. The following describes each part of the prediction unit 700.

[0027] The short-term forecasting unit 710 has the function of predicting short-term wind speeds in the future using a short-term forecasting model created based on data stored in the wind condition observation database 610 or the SCADA database 620. Specifically, the short-term forecasting unit 710 includes a short-term data preprocessing unit 711, a short-term wind condition learning unit 712, and a short-term calculation unit 713.

[0028] The short-term data preprocessing unit 711 processes wind condition observation data read from the wind condition observation database 610 or SCADA data read from the SCADA database 620 to create training data for machine learning. The short-term wind condition learning unit 712 uses the training data from the short-term data preprocessing unit 711 to create a short-term prediction model. The short-term calculation unit 713 uses the short-term prediction model to perform calculations on the latest wind condition observation data read from the wind condition observation database 610 or the latest SCADA data read from the SCADA database 620. This calculates the predicted wind speed for a short period, including the wind power generation forecast period.

[0029] The long-term forecasting unit 720 has the function of correcting meteorological analysis data using a long-term forecasting model created based on SCADA data stored in the SCADA database 620 and meteorological analysis data stored in the meteorological analysis database 630. Specifically, the long-term forecasting unit 720 includes a long-term data preprocessing unit 721, a long-term wind condition learning unit 722, and a long-term calculation unit 723.

[0030] The long-term data preprocessing unit 721 processes SCADA data read from the SCADA database 620 and meteorological analysis data read from the meteorological analysis database 630 to create training data for machine learning. The long-term wind condition learning unit 722 uses the training data from the long-term data preprocessing unit 721 to create a long-term forecasting model. The long-term calculation unit 723 uses the long-term forecasting model to process the latest meteorological analysis data read from the meteorological analysis database 630. This calculates correction data for long-term meteorological analysis data, including the forecast period for wind power generation.

[0031] The power generation prediction unit 730 has the function of predicting wind power generation using a generator model created based on SCADA data stored in the SCADA database 620. Specifically, the power generation prediction unit 730 includes a generator data preprocessing unit 731, a power generation learning unit 732, and a power generation calculation unit 733.

[0032] The generator data preprocessing unit 731 processes SCADA data read from the SCADA database 620 to create training data for machine learning. The power generation learning unit 732 uses the training data created by the generator data preprocessing unit 731 within the neural network NN2 to create a generator model for predicting wind power generation. The power generation calculation unit 733 uses the short-term predicted wind speed calculated by the short-term prediction unit 710 and the correction data calculated by the long-term prediction unit 720 to perform calculations using the generator model created by the power generation learning unit 732. This calculates the wind power generation for the prediction period.

[0033] The results display unit 740 displays various images, such as the amount of wind power generation calculated by the power generation prediction unit 730. The results display unit 740 has a display device such as a liquid crystal display. In this embodiment, the results display unit 740 is configured as part of the prediction unit 700, but it may be configured independently of the prediction unit 700.

[0034] Next, with reference to Figure 6, a method for predicting wind power generation using the wind power generation prediction system 1 according to this embodiment will be described. Figure 6 is a flowchart showing the operation procedure for predicting wind power generation using the wind power generation prediction system 1 according to this embodiment. The operations performed according to the steps in this flowchart can also be realized by having a computer execute a program that processes each step. This program can also be recorded on a recording medium as software.

[0035] In the flowchart shown in Figure 6, first, in the data analysis processing unit 500, the communication unit 510 acquires wind condition observation data from the wind condition observation unit 100, SCADA data from the wind farm monitoring control unit 200, and weather forecast data from the weather forecast data acquisition unit 300 via the communication network 400 (step S11).

[0036] Next, in the data analysis processing unit 500, the data processing unit 520 performs primary processing of wind condition observation data and SCADA data, while the weather forecast data analysis unit 530 analyzes the weather forecast data (step S12). Here, an example of the weather analysis method of the weather forecast data analysis unit 530 will be explained with reference to Figures 7(a) to 7(d).

[0037] Figure 7(a) schematically shows the spatial resolution of weather forecast data, and Figure 7(b) is an example of weather forecast data. Figure 7(c) schematically shows the spatial resolution of meteorological analysis data, and Figure 7(d) is an example of meteorological analysis data.

[0038] The weather forecast data analyzed by the weather forecast data analysis unit 530 is created in grid units when the analysis area, which includes the installation area of ​​the wind farm for which wind power generation is to be predicted and its surrounding area, is divided into a grid, as shown in Figure 7(a). Note that the wind farm for which prediction is to be made shown in Figure 7(a) is an offshore wind farm, but it may also be an onshore wind farm.

[0039] Figure 7(b) shows the weather forecast data for grid point A shown in Figure 7(a). This weather forecast data includes, for example, the north-south wind speed, east-west wind speed, temperature, and the change in temperature over time at grid point A. Although Figure 7(b) shows the weather forecast data for one altitude at grid point A, the weather forecast data for grid point A is created for multiple altitudes that are set in stages in advance. Furthermore, the data analyzed includes not only the weather forecast data for grid point A, but also the weather forecast data for other grid points.

[0040] As shown in Figure 7(c), the weather forecast data analysis unit 530 divides the analysis area into smaller grids than the weather forecast data, according to the required forecast accuracy. This results in a higher spatial resolution than the weather forecast data. The weather forecast data analysis unit 530 creates weather analysis data for each grid point by performing nesting using a WRF analysis model such as a numerical weather model, with the weather forecast data as input data.

[0041] Figure 7(d) shows meteorological analysis data for one altitude at grid point a. This meteorological analysis data shows, for example, north-south wind speed, east-west wind speed, temperature, and the change in temperature over time at grid point a. In this case, while the weather forecast data shows changes over time in one-hour increments, the meteorological analysis data shows changes over time in ten-minute increments. Therefore, the temporal resolution of the meteorological analysis data is also higher than that of the weather forecast data. Note that although Figure 7(d) shows meteorological analysis data for one altitude at grid point a, the meteorological analysis data for grid point a is created for multiple altitudes, just like the weather forecast data. In addition, the meteorological analysis data includes data not only for grid point a but also for other grid points.

[0042] As described above, the meteorological analysis data created by the meteorological forecast data analysis unit 530 is stored in the meteorological analysis database 630 (step S13). In step S13, the wind condition observation data and SCADA data that have been primary processed by the data processing unit 520 are stored in the wind condition observation database 610 and the SCADA database 620, respectively.

[0043] Next, the long-term forecasting unit 720 of the forecasting unit 700 performs a long-term forecast of wind speed (step S14). Now, with reference to Figure 8, the operation of step S14 will be explained.

[0044] Figure 8 is a schematic diagram illustrating an example of the long-term forecasting method of the long-term forecasting unit 720. In step S14, first, the long-term data preprocessing unit 721 of the long-term forecasting unit 720 reads past SCADA data from the SCADA database 620 and past meteorological analysis data from the meteorological analysis database 630. The past SCADA data and past meteorological analysis data read by the long-term data preprocessing unit 721 include, for example, past data for the same time as the wind power generation forecast time. Subsequently, the long-term data preprocessing unit 721 processes the read SCADA data and meteorological analysis data to create training data for machine learning.

[0045] Next, the long-term wind condition learning unit 722 creates a long-term prediction model based on machine learning using the training data created by the long-term data preprocessing unit 721. In this embodiment, this long-term prediction model is a mathematical model that can be used in the neural network NN1.

[0046] Finally, the long-term calculation unit 723 reads the latest weather analysis data from the weather analysis database 630. Subsequently, the long-term calculation unit 723 processes the read weather analysis data using the long-term forecast model described above as input data. As a result, correction data for the weather analysis data is calculated. This correction data is wind speed correction data for the wind turbine installation locations that are the target of the wind power generation forecast.

[0047] The wind speed correction data described above is calculated using a long-term prediction model generated by machine learning with historical data as training data. Therefore, as shown in Figure 8, the error between the wind speed correction data and the actual measured wind speed data is smaller for the wind speed correction data than for the meteorological analysis data. Note that the method for calculating the correction data is not limited to the method described above.

[0048] As described above, once the long-term forecasting unit 720 has completed its long-term forecast, the short-term forecasting unit 710 of the forecasting unit 700 then performs a short-term forecast of wind speed (step S15). Now, with reference to Figure 9, the operation of step S15 will be explained.

[0049] Figure 9 is a schematic diagram illustrating an example of the short-term forecasting method of the short-term forecasting unit 710. In step S15, first, the short-term data preprocessing unit 711 of the short-term forecasting unit 710 reads past SCADA data from the SCADA database 620 or past wind condition observation data from the wind condition observation database 610. The past SCADA data or past wind condition observation data read by the short-term data preprocessing unit 711 includes, for example, past data for the same time as the wind power generation forecast time.

[0050] The decision of whether the short-term data preprocessor 711 reads SCADA data or wind condition observation data is predetermined according to the content of the short-term forecast model described later. If a measurement item that is not present in the SCADA data but is present in the wind condition observation data, such as the wind speed standard deviation, is necessary for creating the short-term forecast model, the short-term data preprocessor 711 reads the wind condition observation data. In this case, the short-term data preprocessor 711 processes the read wind condition observation data to create training data for machine learning. If the short-term data preprocessor 711 reads SCADA data, it processes this SCADA data to create training data for machine learning.

[0051] Next, the short-term wind condition learning unit 712 creates a short-term prediction model based on machine learning using the training data created by the short-term data preprocessing unit 711. In this embodiment, this short-term prediction model is a mathematical model that can be used in a recurrent neural network RNN1.

[0052] Finally, the short-term calculation unit 713 reads the latest SCADA data from the SCADA database 620 or the latest wind condition observation data from the wind condition observation database 610. Subsequently, the short-term calculation unit 713 processes the read SCADA data or wind condition observation data using the short-term prediction model described above. As a result, the short-term predicted wind speed is calculated. If the input data is SCADA data, this short-term predicted wind speed is wind speed data at the installation site of the wind turbine that is the target of the wind power generation forecast. On the other hand, if the input data is wind condition observation data, this short-term predicted wind speed is wind speed data at the wind condition observation point within the wind power generation forecast area.

[0053] The short-term wind speed forecasts mentioned above are calculated using a short-term prediction model generated by machine learning with historical measurement data as training data. In other words, the short-term prediction model is created using only measurement data, without any prediction data. Therefore, it is possible to calculate short-term wind speeds at wind power generation forecast locations with high accuracy. Note that the method for calculating short-term wind speed forecasts is not limited to the method described above.

[0054] As described above, once the short-term prediction unit 710 has completed its short-term prediction, the power generation prediction unit 730 of the prediction unit 700 then performs a wind power generation prediction (step S16). Now, with reference to Figure 10, the operation of step S16 will be explained.

[0055] Figure 10 is a schematic diagram illustrating an example of the power generation prediction method of the power generation prediction unit 730. In step S15, first, the generator data preprocessing unit 731 of the power generation prediction unit 730 reads past SCADA data from the SCADA database 620. The past SCADA data read by the generator data preprocessing unit 731 includes, for example, past data for the same time as the wind power generation prediction time. Subsequently, the generator data preprocessing unit 731 processes the read SCADA data to create training data for machine learning.

[0056] Next, the power generation learning unit 732 creates a generator model based on machine learning using the training data created by the generator data preprocessing unit 731. In this embodiment, this generator model is a mathematical model that can be used in a neural network NN2.

[0057] Finally, the power generation calculation unit 733 processes the short-term predicted wind speed calculated by the short-term prediction unit 710 and the correction data calculated by the long-term prediction unit 720 as input data using the generator model described above. As a result, the predicted power generation is calculated. This predicted power generation is displayed on the results display unit 740 as a graph showing the relationship between wind speed and power generation based on SCADA data, for example, as shown in Figure 10.

[0058] In a wind farm, wind power generation depends on wind speed. Wind speed can change not only over long periods of several hours, but also over short periods of several seconds. Therefore, when predicting short-term wind power generation, predicting wind power generation based only on short-term wind speed forecasts will result in insufficient accuracy.

[0059] Therefore, in this embodiment, the long-term prediction unit 720 predicts wind conditions for a long period (first period) including the wind power generation prediction period, and the short-term prediction unit 710 predicts wind conditions for a short period (second period) including the above prediction period. Furthermore, the power generation calculation unit 733 calculates the wind power generation for the above prediction period using the prediction results of the long-term prediction unit 720 and the prediction results of the short-term prediction unit 710. In this way, by predicting wind power generation using not only the short-term predicted wind speed but also the long-term predicted wind speed, it becomes possible to predict short-term wind power generation with high accuracy.

[0060] (First variation) Figure 11 is a block diagram showing the configuration of the prediction unit 700 according to the first modified example. In Figure 11, the same reference numerals are used for the same components as in the embodiments described above, and detailed explanations are omitted.

[0061] In this modified example, the short-term forecasting unit 710 calculates the short-term predicted wind speed using the correction data, which is the prediction result of the long-term forecasting unit 720. Now, with reference to Figure 12, the short-term wind speed forecasting method according to this modified example will be explained.

[0062] Figure 12 is a graph showing an example of comparing wind speed prediction results with actual measurement results. In Figure 12, the horizontal axis represents time, and the vertical axis represents wind speed. The solid line represents the prediction results of the short-term prediction unit 710, the dashed line represents the prediction results of the long-term prediction unit 720, and the dotted line represents the actual measurement results. In Figure 12, at time t0, the wind speed predicted by the long-term prediction unit 720 changes significantly. If the amount of change in wind speed at this time exceeds a preset reference value, the short-term prediction unit 710 calculates the short-term predicted wind speed using the prediction results of the long-term prediction unit 720. Specifically, when the short-term wind condition learning unit 712 of the short-term prediction unit 710 creates a short-term prediction model, it sets weighting coefficients for the short-term prediction model according to the prediction results of the long-term prediction unit 720.

[0063] As described above, once the short-term wind condition learning unit 712 creates a short-term prediction model, the short-term calculation unit 713 performs calculations using that short-term prediction model to calculate the short-term predicted wind speed. Subsequently, the power generation prediction unit 730 predicts the amount of wind power generated based on the short-term predicted wind speed. Finally, the result display unit 740 displays the prediction result from the power generation prediction unit 730.

[0064] In the modified version described above, the wind power generation amount is predicted by reflecting the prediction results of the long-term prediction unit 720 in the prediction results of the short-term prediction unit 710. Therefore, in this modified version as well, the wind power generation amount is predicted using the prediction results of the long-term prediction unit 720 and the prediction results of the short-term prediction unit 710. Thus, it becomes possible to predict short-term wind power generation with high accuracy.

[0065] (Second variation) Figure 13 is a block diagram showing the configuration of the prediction unit 700 according to the second modified example. In Figure 13, the same reference numerals are used for the same components as in the embodiments described above, and detailed descriptions are omitted.

[0066] In this modified example, the prediction unit 700 further includes a wind speed correction unit 750. The wind speed correction unit 750 corrects the wind speed of the wake turbines in the wind farm using a wake model. The wake model will now be explained with reference to Figures 14 and 15.

[0067] Figure 14 is a schematic diagram showing the arrangement of wind turbines in a wind farm. Figure 15 is a diagram showing an example of wind speed changes between upstream and wake turbines.

[0068] As shown in Figure 14, for example, if the wind direction is westward, moving from left to right on the diagram, the upstream wind turbine is located on the windward side towards the west, and the wake wind turbine is located on the leeward side towards the east. In this case, as shown in Figure 15, from time t1 to time t2, the wind speed of the wake wind turbine is reduced due to the influence of the upstream wind turbine, and from time t2 to time t3, the wind speed of the wake wind turbine becomes approximately equal to the wind speed of the upstream wind turbine.

[0069] The wind speed reduction of wake turbines caused by upstream wind turbines affects the amount of power generated by wake turbines. The wake model is a mathematical model for calculating the degree to which the wind speed reduction of wake turbines caused by upstream wind turbines affects the amount of power generated by wake turbines. The wind speed correction unit 750 uses wind direction data included in the wind conditions predicted by the short-term forecast unit 710 and the long-term forecast unit 720 to identify wake turbines affected by the wind speed reduction caused by upstream wind turbines based on the wind turbine installation location and positional relationship within the wind farm. Subsequently, the wind speed correction unit 750 corrects the wind speed of the wake turbines using the wake model.

[0070] Therefore, according to this modified version, the wind speed of the downstream wind turbine can be corrected from the wind speed of the upstream wind turbine predicted by the short-term prediction unit 710 and the long-term prediction unit 720, respectively, thus improving the accuracy of wind speed prediction. As a result, the accuracy of the wind power generation amount predicted based on the corrected wind speed of the downstream wind turbine is also improved.

[0071] While embodiments and modifications have been described above, these embodiments and modifications are presented for illustrative purposes only and are not intended to limit the scope of the invention. The novel system described herein can be implemented in a variety of other forms. Furthermore, various omissions, substitutions, and modifications can be made to the forms of the system described herein without departing from the spirit of the invention. The appended claims and equivalents are intended to include such forms and modifications that fall within the scope and spirit of the invention. [Explanation of symbols]

[0072] 1: Wind power generation forecasting system 100: Wind Condition Observation Department 200: Wind Farm Monitoring and Control Unit 300: Weather forecast data acquisition unit 530: Weather Forecast Data Analysis Department 600: Storage section 700: Prediction Department 710: Short-term forecasting section 711: Short-term data preprocessing unit 712: Short-term wind conditions learning department 713: Short-term calculation unit 720: Long-term forecasting section 721: Long-term data preprocessing unit 722: Long-term wind conditions learning department 723: Long-term calculation unit 730: Power generation forecasting unit 731: Generator data preprocessing unit 732: Power Generation Learning Unit 733: Power generation calculation unit 750: Wind speed correction section

Claims

1. a wind condition observation unit that measures wind conditions at a wind farm for which wind power generation is to be predicted; a wind farm monitoring control unit that records measurement data measured at installation positions of wind turbines in the wind farm to be predicted; a weather forecast data acquisition unit that acquires weather forecast data for an area including the wind farm to be predicted; a storage unit for storing wind condition observation data indicating the measurement results of the wind conditions, the measurement data, and meteorological analysis data indicating the analysis results of the weather forecast data; a prediction unit that uses the data stored in the storage unit to predict wind conditions for a first period that includes a prediction period for the wind power generation amount and for a second period that includes the prediction period but is shorter than the first period, and predicts the wind power generation amount based on the wind condition prediction results for the first period and the second period; A wind power generation forecasting system equipped with the above.

2. The wind power generation prediction system according to claim 1 , wherein the prediction unit predicts the wind conditions for the second time period using a result of the wind conditions prediction for the first time period.

3. the prediction unit includes a short-term prediction unit that predicts wind conditions for the second period, The short-term prediction unit a short-term data preprocessing unit that processes the wind observation data or measurement data read from the storage unit to create training data for machine learning; a short-term wind condition learning unit that creates a short-term forecast model based on machine learning using the training data; The wind power generation prediction system according to claim 1 , further comprising: a short-term calculation unit that calculates the wind conditions for the second time period by performing calculation processing using the short-term prediction model.

4. The wind power generation amount prediction system according to claim 3 , wherein the short-term calculation unit performs calculation processing based on the short-term prediction model within a recurrent neural network.

5. the prediction unit includes a long-term prediction unit that predicts wind conditions for the first period, The long-term prediction unit a long-term data preprocessing unit that processes the measurement data and meteorological analysis data read from the storage unit to create training data for machine learning; a long-term wind condition learning unit that creates a long-term forecast model based on machine learning using the training data; The wind power generation prediction system according to claim 1 , further comprising: a long-term calculation unit that calculates the wind conditions for the first period by performing calculation processing using the long-term prediction model.

6. the prediction unit includes a power generation amount prediction unit that predicts the wind power generation amount, The power generation amount prediction unit a generator data preprocessing unit that processes the measurement data read from the storage unit to create training data for machine learning; a power generation amount learning unit that creates a power generator model based on machine learning using the training data; The wind power generation amount prediction system according to claim 1 , further comprising: a power generation amount calculation unit that calculates the wind power generation amount by calculation processing using the generator model.

7. The wind power generation amount prediction system according to claim 6 , wherein the power generation amount calculation unit performs calculation processing based on the generator model within a neural network.

8. a weather forecast data analysis unit that analyzes the weather forecast data acquired from the weather forecast data acquisition unit and outputs the weather analysis data; 8. The wind power generation prediction system according to claim 1, wherein the weather forecast data analysis unit adjusts the temporal resolution and spatial resolution of the weather forecast data according to a required prediction accuracy and outputs the weather analysis data.

9. An upstream wind turbine arranged on the upwind side and a wake wind turbine arranged on the downwind side are installed in the wind farm to be predicted, 9. The wind power generation prediction system according to claim 1, wherein the prediction unit includes a wind speed correction unit that corrects the wind speed of the wake wind turbine using a wake model for calculating an effect of a wind speed deceleration of the wake wind turbine caused by the upstream wind turbine on the amount of power generation of the wake wind turbine.

10. Measure the wind conditions at the wind farm for which wind power generation is to be predicted, recording measurement data measured at installation positions of wind turbines within the wind farm to be predicted; Obtaining weather forecast data for an area including the wind farm to be predicted; storing wind condition observation data indicating the measurement results of the wind conditions, the measurement data, and meteorological analysis data indicating the analysis results of the weather forecast data in a storage unit; using the data stored in the storage unit, predicting wind conditions for a first period including a prediction period of the wind power generation amount and for a second period including the prediction period but shorter than the first period; predicting the amount of wind power generation based on wind condition prediction results for the first period and the second period; Wind power generation forecasting methods.

11. Measure the wind conditions at the wind farm for which wind power generation is to be predicted, recording measurement data measured at installation positions of wind turbines within the wind farm to be predicted; Obtaining weather forecast data for an area including the wind farm to be predicted; storing wind condition observation data indicating the measurement results of the wind conditions, the measurement data, and meteorological analysis data indicating the analysis results of the weather forecast data in a storage unit; using the data stored in the storage unit, predicting wind conditions for a first period including a prediction period of the wind power generation amount and for a second period including the prediction period but shorter than the first period; A program for causing a computer to execute a process for predicting the amount of wind power generation based on wind condition prediction results for the first period and the second period.

Images