Application of Multilayer Perceptron (MLP) Neural Networks in Wind Speed Forecasting: A Study in the Interior of the State of Pernambuco

- 326284
Extended Abstracts (EA)
Favorite this paper
How to cite this paper?
Abstract

This study applies MLP Artificial Neural Networks to predict wind speed in meteorological stations in Pernambuco, using 15 atmospheric variables obtained through INMET. The iterative autoregressive approach makes short-term predictions with a 24-hour horizon. The performance was evaluated by error metrics (MAE, RMSE, MAPE), showing good performance in regions with stable wind patterns.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Universidade Federal de Pernambuco
  • 2 Universidade Federal do Piauí
  • 3 UFPB - Universidade Federal da Paraíba
  • 4 UFPE - Universidade Federal de Pernambuco
  • 5 Chesf - Companhia Hidro Elétrica do São Francisco
  • 6 ONS - Operador Nacional do Sistema Elétrico
Track
  • 7. EN&OG – OR in Energy, Oil and Gas
Keywords
Wind Speed Forecasting
Artificial Intelligence
Artificial Neural Networks
Multilayer Perceptron (MLP)
Wind Energy in Pernambuco