Floating offshore wind turbines (FOWT) hold great potential for future solutions to the ever growing demand for renewable energy production; now while this market is growing more rapidly in European countries and within in United States, Thereafter, the prediction of total amounts of offshore wind power generation of the location became critical in locating and designing wind farms and turbines, where the prediction of the wind speed plays a role as one of the fundamental parameters. The purpose of this research is to improve the prediction of the local wind speed and the expected power generation by using Deep Learning (DL), a recently developed computational data science method. Deep Neural Network is designed and tested using both Long Short-Term Memory (LSTM) and Bi-directional LSTM (BLSTM) to capture long-term time-dependency. The selected networks for this research are refined by tuning the associated parameters of each layers and the network. The networks are trained and tested using sets of weather data including wind speed gathered under the National Oceanic and Atmospheric Administration (NOAA). Predicted wind speed data using the trained network and testing data sets are presented to compare to the observed wind data. To evaluate the capability of the trained networks, Root Mean Square Error (RMSE) of the predictions from the various length of testing data are presented per two variables: the number of training data and the target prediction length of meteorological future. The predictions of the wind power generation are presented along with the wind speed and the prediction error envelopes.  The research is beneficial for establishing more complex prediction models with higher levels of accuracy and can be transitioned to define optimum locations for FOWT farms.  


Prediction of Wind Speed, Potential Wind Power, and the Associated Uncertainties for Offshore Wind Farm Using Deep Learning

Division / Sponsors: 
Power Division & Nuclear Engineering Division (NED)

Power Conference
Paper Proceedings: https://asmedigitalcollection.asme.org/POWER/POWER2020/volume/83747

International Conference on Nuclear Engineering
Paper Proceedings: https://asmedigitalcollection.asme.org/ICONE/ICONE2020/volume/83761

POWER-ICONE - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.