Research Article
A Two-Step Approach for Forecasting Wind Speed at Offshore Wind Farms During Typhoons
@INPROCEEDINGS{10.1007/978-3-031-31733-0_9, author={Xuan Liu and Jun Guo}, title={A Two-Step Approach for Forecasting Wind Speed at Offshore Wind Farms During Typhoons}, proceedings={Smart Grid and Innovative Frontiers in Telecommunications. 7th EAI International Conference, SmartGIFT 2022, Changsha, China, December 10-12, 2022, Proceedings}, proceedings_a={SMARTGIFT}, year={2023}, month={5}, keywords={Wind Speed Prediction Offshore Wind Farm Typhoon Neural Network LSTM Seq2seq}, doi={10.1007/978-3-031-31733-0_9} }- Xuan Liu
Jun Guo
Year: 2023
A Two-Step Approach for Forecasting Wind Speed at Offshore Wind Farms During Typhoons
SMARTGIFT
Springer
DOI: 10.1007/978-3-031-31733-0_9
Abstract
Wind power has become the leading factor in the transition from fossil fuels to renewable energy sources. The total capacity of offshore wind farms in China has increased significantly in the past decade. It’s essential to understand the risk posed by typhoons to offshore wind farms. However, the impacts of typhoons are hard to predict due to the limited number of observations. In this study, a deep learning-based two-step approach is proposed for estimating the wind speed of given locations during typhoons. An LSTM-based seq2seq model is implemented in the first step to predict the typhoon track and intensity. In the second step, a linear wind field model is adopted to calculate the wind speed at specific locations. The case study results show that the proposed approach is capable of predicting the extreme wind speed at specific offshore locations during typhoons. This study demonstrates the potential of assessing wind risk with a combination of data-driven and physics-based models.
