Please enable JavaScript.
Coggle requires JavaScript to display documents.
Modeling Wind Speed with a Long-Term Horizon and High-Time Interval with a…
Modeling Wind Speed with a Long-Term Horizon and High-Time Interval with a Hybrid Fourier-Neural Network Model
-
METHODOLOGY
Given the nonlinearities of the WS variations, a NAR model is used to forecast the WS based on the variability identified with the Fourier analysis
-
-
-
NARR data was used to have values of the WS in Barranquilla, Colombia.
RESULTS AND DISCUSSION
-
The Fourier model was validated with a scattering analysis by correlating the raw data and the model results
-
Evaluating the performance of the Fourier-NAR model and the NAR model, this study evidence that Fourier-NAR model outperform the NAR model
-
A time horizon of 1.71 years was considered in the Fourier model to generate the imput data used in the NAR model
-
Conclusions
The hybrid Fourier-NAR model can accurately forecast the WS in a scale of 1.7 yeras of time horizons at 3 hours
-
-
-
-
