A Short-Term Wind Speed ​​Forecasting Method Based on Deep Neural Network Migration Model

Abstract

The invention discloses a short-term wind speed forecasting method based on a deep neural network transfer model. The method comprises the following steps that (1) normalization preprocessing and division of sample sets are carried out on data of two or more wind power plants, (2) the deep neural network transfer model is established, (3) layered training is started from bottom to top in an unsupervised learning mode, (4) supervised learning is carried out from top to bottom on the basis of the third step, (5) weight parameters of connection of a top layer and hidden layers are finely adjusted so as to obtain an output layer, corresponding to the wind power plants, in a deep neural network, and (6) inverse normalization is carried out on the result output by a deep neural network so as to obtain the predicted value of wind speed. Transfer learning is introduced to the wind speed forecasting field, knowledge of other wind power plants rich in data is transferred to target wind power plants, and the problem that the newly built wind power plants have few data is solved effectively. By means of the effective transfer scheme based on the deep neural network, the wind speed prediction accuracy of the target wind power plants is greatly improved.

Description

technical field [0001] The present invention is based on machine learning theory and statistical learning theory, by constructing a regression model based on deep neural network, on this basis, constructing a multi-output deep migration model with shared hidden layers, and finally using this model for wind farms with less data short-term wind speed forecast. Background technique [0002] In terms of wind speed forecasting, many methods have been proposed. These methods can be divided into four categories: 1) physical models; 2) statistical models; 3) spatial correlation models; 4) artificial intelligence models and other new models. Physical models use physical factors, weather data such as topography, pressure and temperature to estimate future wind speeds. It has advantages in long-term forecasting, but generally cannot give accurate results in short-term forecasting. As such, they are often only the first step in predictions, as auxiliary inputs to other models. The s...

AI Technical Summary

Problems solved by technology

The invention introduces transfer learning into the field of wind speed prediction, and effectively solves the problem of less data in new wind farms by transferring the knowledge of other data-rich wind farms to the target wind farm

Images