Impact of Environmental Data on Wind Turbine Noise Level Estimation
Rkhiss A*, Finez A, Gloaguen J-R, Vasiele G and Maillard J
ABSTRACT
Wind energy is one of the most widely used renewable energy sources in the world and has grown rapidly in recent years. However, wind turbines generate noise that is often perceived as a disturbance by nearby residents. So, developing tools to assist wind farm developers and regulatory authorities is essential. This study focusses on the impact of environmental data on wind turbine noise (WTN) level estimation using recurrent neural networks (RNNs). We compare the performance of an architecture which is based on long-short term memory cells (LSTM). LSTM model trained using only acoustic features in the frequency range of 31.5 Hz to 2 kHz with those incorporating additional environmental features, such as wind speed and wind turbine power accorded to each wind speed value. The results highlight the influence of these factors on noise characterization and demonstrate the extent to which environmental data enhances WTN level estimation.
