Multi-step wind speed prediction based on turbulence intensity and hybrid deep neural networks

Energy Conversion and Management has published a paper by Professor Jay Lee and PhD Researcher Fei Li of the IMS Center titled Multi-Step Wind Speed Prediction Based on Turbulence Intensity and Hybrid Deep Neural Networks.

This paper can be downloaded Here.

A Multi-Step Wind Speed Prediction Based on Turbulence Intensity and Hybrid Deep Neural Networks

Energy Conversion and Management Volume 186, 15 April 2019, Pages 306-322

Turbulence intensity of wind speed is a viable uncertainty quantification for wind speed. This paper develops an innovative framework for multi-step wind speed prediction using Wind Speed and Turbulence Intensity-based Recursive Neural Network. In this study, real-time turbulence intensity is measured from actual wind speed, and multi-resolution features of wind speed and turbulence intensity are deployed as input for prediction model. Ensemble recursive neural network is designed to execute prediction on multiple prediction intervals ranging from 10 min to 12 h with two different integrating strategies. Experimental results indicate that: (1) The proposed model dramatically outperforms conventional machine learning models on multi-step wind speed prediction; (2) The reliable wind speed prediction requires that the maximum time-resolution of turbulence intensity should be longer than prediction interval; (3) Turbulence intensity features involved prediction will achieves higher accuracy than the approaches that apply signal processing on raw wind speed, especially on middle-long term prediction. Therefore, this innovative scheme for multi-step wind speed prediction can be of immense utility to apply data-driven methods for accurate long-term wind speed prediction..

For more information about this work, or to find out how you can collaborate with our Center, contact the IMS Center today at:


Featured in this Article
Professor Jay Lee
Fei Li