Method for predicting wind speed and power of wind farm based on wavelet decomposition and support vector machine

Abstract

The invention discloses a method for predicting wind speed and power of a wind farm based on wavelet decomposition and a support vector machine. The method comprises: acquiring wind speed and power historical data of a whole wind farm in a preset time, to obtain a historical wind speed time sequence and a historical power time sequence of the wind farm; using a wavelet packet decomposition technology to perform wavelet packet decomposition on the historical wind speed time sequence, to obtain a low-frequency stage component, a middle-frequency stage component, and a high -frequency stage component of the historical wind speed time sequence; using a grey support vector machine prediction model to predict each component of the historical wind speed time sequence, and then using wavelet packet reconstruction to obtain short-period wind speed prediction data; using historical wind electricity power data and numerical weather prediction wind speed data as a training set to establish a grey support vector machine model, predicting wind electricity power; predicting the obtained wind speed prediction data and the wind electricity power prediction data through a RBF neural network, to obtain a final prediction value of the wind electricity power.

Description

technical field [0001] The invention relates to the technical field of new energy power generation, in particular to a method for predicting wind speed and power of a wind farm based on wavelet decomposition and support vector machines. Background technique [0002] The development and utilization of renewable energy, especially wind energy, has been highly valued by countries all over the world. Wind power is currently the most mature technology and the most promising renewable energy for large-scale development. Due to the strong randomness of wind power generation, the accuracy of wind farm power forecasting is not satisfactory. The development of wind power forecasting systems is relatively seldom, and there is a lack of mature practical experience. [0003] The current research and application of wind speed or power generation forecasting in wind farms can be divided into short-term wind power forecasting and ultra-short-term wind power forecasting in terms of forecast...

AI Technical Summary

Problems solved by technology

Existing wind power forecasting mostly uses a single model or a simple combination of multiple models to predict the wind power sequence. The models do not cooperate well, and the forecasting steps are complicated and repeated.

Moreover, most of the existing wind power forecasting is to first predict the wind speed, and then derive the wind power forecast through formula derivation, which ignores many influencing factors of wind power forecasting and reduces the accuracy of wind power forecasting

Images