Wind Power Prediction Method and Device Based on Gathering Different Climate Characteristics of Local Multiple Points

Abstract

The present invention provides a method and device for wind power forecasting based on the collection of local multi-point and different climate characteristics. The method includes establishing an electric field model, obtaining meteorological numerical forecast results around the electric field, and obtaining a single-point forecast wind speed in three-dimensional space through a data interpolation method. The value of the single-point forecast wind speed is synthesized into two or three-point wind speeds to obtain the composite wind speed; the synthetic wind speed is converted into wind power by using the neural network method. On the basis of the original single-point forecast, the present invention integrates the single-point results to form a multi-point aggregate forecast, reduces wind speed fluctuations, and improves the accuracy of wind power prediction; the meteorological data collected by the present invention selects horizontal and vertical three-dimensional high-resolution Grid points, which integrate climate conditions at different levels and heights, improve the accuracy of wind power prediction; the invention reduces wind field volatility by integrating multi-point climate characteristics, and is not affected by factors such as electric field expansion and power limitation, and adjusts Forecast wind speed and improve the accuracy of wind power prediction.

Description

technical field [0001] The invention belongs to the technical field of wind farm power forecasting and forecasting, and in particular relates to a wind power forecasting method and device based on gathering local multi-point different climate characteristics. Background technique [0002] Wind power is a clean and renewable energy source. By the end of 2015, the cumulative installed capacity of wind power in the world reached 432,419MW, of which China accounted for 48.4% of the total capacity. Because wind power generation is affected by changes in wind speed and wind direction, this makes wind power generation have obvious volatility, intermittent and randomness, which has a great impact on the safety and stable operation of the power system, and through accurate wind power prediction , the short-term forecast of the output of wind farms can effectively regulate the operation and maintenance of the farm and reduce the loss of electricity. Therefore, accurate wind power fore...

AI Technical Summary

Problems solved by technology

[0005] The chaotic characteristics of the atmosphere make it difficult to predict the meteorological results of a single point even if the best numerical model in the world is used. The systematic error and wrong forecast of the model itself will indirectly lead to the forecast error of wind speed

[0006] Since the current power modeling technology is based on the average wind speed of the fans in the whole field, which represents the overall climate state of the whole field, it is difficult to describe the average wind speed state of the whole field by only roughly selecting a single point according to the arrangement of the fans in the electric field, and it cannot be accurate captures the climatic state of the farm, therefore, forecasted wind speeds are not appropriate for wind farms

[0007] The spatial span of the electric field is large, and the altitudes of different electric fields are also different. The wind speed in the boundary layer changes significantly with height, which will lead to great differences in the climate characteristics of different electric fields. Only the results of single-layer or hub height in the numerical model are used. will be very inaccurate

[0008] To sum up, according to the layout of wind turbines, artificially select a geographical coordinate, and finally interpolate the grid point data of numerical weather prediction to this point, so that it cannot accurately reflect the overall climate characteristics of the entire wind farm, and ultimately lead to the wind power prediction accuracy not ideal

Images