A wind speed prediction method based on a depth limit learning machine and a system and a unit thereof

Abstract

The invention discloses a wind speed prediction method based on a depth limit learning machine, a system and a generator set thereof, belonging to the field of wind turbine generators. The wind speedvalue is predicted by the time series prediction method of the depth limit learning machine, which comprises the following steps: acquiring a group of historical observation data series at time t andbefore time t in the generation process of the wind turbine; extracting the training sample data set by the time series prediction method of depth limit learning machine, performing derivation of theprediction model: the nearest neighbor of the prediction sequence Q is extracted from the training sample data set as the recombination sample, when the recombination sample corresponds to single-stepprediction, the multi-step prediction has the single-step feature and the multi-step feature, training the DELM models with single-step feature and multi-step feature and multi-hidden layer by depthlimit learning machine, and integrating into a prediction model through local selection, and predicting the wind speed value Xt + s by the prediction model. The method of the invention has high accuracy and generalization performance, and can improve prediction performance and real-time update capability.

Description

technical field The invention relates to the field of wind turbines, in particular to a wind speed prediction method based on a deep extreme learning machine, its system and the wind turbine. Background technique As an important part of the national sustainable development strategy, wind power converts air kinetic energy into electrical energy, and the random fluctuation and intermittency of wind determine the fluctuation and intermittency of wind power. With the continuous expansion of the scale of wind power generation, the impact of wind farm grid connection on the grid system will become more and more obvious. Large wind speed disturbances will cause great changes in the voltage and frequency of the system. The stability and security issues in the future have become new issues that need to be solved urgently. Therefore, accurate prediction of wind speed is beneficial to the operation of wind turbines in wind farms, which is subject to system operating conditions, and ca...

AI Technical Summary

Problems solved by technology

It can effectively improve the shortcomings of traditional neural networks such as low learning efficiency, easy to fall into local optimum, and the number of network layers restricts the training effect.

Images