Term of Award

Summer 2017

Degree Name

Master of Science in Applied Engineering (M.S.A.E.)

Document Type and Release Option

Thesis (open access)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.


Department of Mechanical Engineering

Committee Chair

Biswanath Samanta

Committee Member 1

David Calamas

Committee Member 2

Minchul Shin


In order to meet the US Department of Energy projected target of 35% of US energy coming from wind by 2050, there is a strong need to study the management and development of wind turbine technology and its impact on human health, wildlife and environment. The prediction of wind turbine noise and its propagation is very critical to study the impacts of wind turbine noise for long term adoption and acceptance by neighboring communities. The prediction of wind speed is critical in the assessment of feasibility of a potential wind turbine site. This work presents a study on prediction of wind turbine noise and wind speed using a noise propagation model and artificial neural network (ANN) methods respectively. The noise propagation model utilized Openwind, a software package used for wind project design and optimization, to predict a noise map based on inputs acquired from a potential wind energy demonstration site in Georgia. The resultant noise of the wind turbines and the ambient surroundings were predicted in the neighborhood for different scenarios. The nonlinear autoregressive (NAR) neural network and nonlinear autoregressive neural network with exogenous inputs (NARX) were used to predict wind speed utilizing one year of hourly weather data from four locations around the US to train, validate, and test these networks. This study optimized both neural network configurations and it was demonstrated that both models were suitable for wind speed prediction. Both models were implemented for single-step and multi-step ahead prediction of wind speed for all four locations and results were compared. NARX model gave better prediction performance than NAR model and the difference was statistically significant.

Research Data and Supplementary Material