Plateau mountain area wind power forecasting method based on different wind speed sections

Abstract

The invention discloses a plateau mountain area wind power forecasting method based on different wind speed sections. The method comprises the following steps that: collecting the geographic coordinates of n pieces of fans of a wind power plant, the topographic map, which contains a coordinate direction, of a wind power plant area, the wind speed data of a numerical value weather forecast, historical wind speed data and a wind direction rose diagram; dividing positions where the n pieces of fans are positioned into a flat area, the front side of a hillside and the back side of the hillside; clustering the historical wind speed data of the area where the wind power plant is positioned to obtain m wind speed sections; utilizing the historical wind speed data of the area where the wind power plant is positioned to aim at three classes of positions to independently carry out segmentation fitting on the wind speed of the m pieces of wind speed sections to obtain a wind speed model which considers the fan position of the plateau mountain area; establishing an annual wind speed set; taking the wind speed set as a sample set to cluster the wind speed to establish the wind power forecasting model of a support vector machine; and calling the wind power forecasting model of the support vector machine to carry out wind power forecasting. By use of the method, the technical problems of low accuracy, big errors and the like since an air return phenomenon and different positions of the fans are not considered can be solved.

Description

technical field [0001] The invention belongs to a wind power prediction method, in particular to a wind power prediction method in plateau mountainous areas based on different wind speed segments. Background technique [0002] Wind power forecasting is a very important link in wind power generation technology. The prior art CN102298707 proposes a wind power forecasting method based on continuous time period clustering and support vector machine modeling. This method considers the daily similarity horizontally At the same time, the continuous information of the training samples in time is considered vertically to enhance the completeness and robustness of the model. However, this method is mainly used in the power prediction of wind turbines in plain areas, and it is directly applied to wind power in plateau mountainous areas. There are great limitations in the prediction, because the mountain roads in the plateau are rugged and the altitude difference is large, which causes ...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a method for forecasting wind power in plateau mountainous areas based on different wind speed s

Images